Moved, renamed, and deleted files

The original directory structure was scattered and unorganized.
Changes are basically to make it look like kernel structure.

51 files changed, 19055 insertions, 0 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
new file mode 100644
index 00000000..ea20c51d
--- /dev/null
+++ b/drivers/xen/Kconfig
@@ -0,0 +1,199 @@
+menu "Xen driver support"
+	depends on XEN
+
+config XEN_BALLOON
+	bool "Xen memory balloon driver"
+	default y
+	help
+	  The balloon driver allows the Xen domain to request more memory from
+	  the system to expand the domain's memory allocation, or alternatively
+	  return unneeded memory to the system.
+
+config XEN_SELFBALLOONING
+	bool "Dynamically self-balloon kernel memory to target"
+	depends on XEN && XEN_BALLOON && CLEANCACHE && SWAP && XEN_TMEM
+	default n
+	help
+	  Self-ballooning dynamically balloons available kernel memory driven
+	  by the current usage of anonymous memory ("committed AS") and
+	  controlled by various sysfs-settable parameters.  Configuring
+	  FRONTSWAP is highly recommended; if it is not configured, self-
+	  ballooning is disabled by default but can be enabled with the
+	  'selfballooning' kernel boot parameter.  If FRONTSWAP is configured,
+	  frontswap-selfshrinking is enabled by default but can be disabled
+	  with the 'noselfshrink' kernel boot parameter; and self-ballooning
+	  is enabled by default but can be disabled with the 'noselfballooning'
+	  kernel boot parameter.  Note that systems without a sufficiently
+	  large swap device should not enable self-ballooning.
+
+config XEN_BALLOON_MEMORY_HOTPLUG
+	bool "Memory hotplug support for Xen balloon driver"
+	default n
+	depends on XEN_BALLOON && MEMORY_HOTPLUG
+	help
+	  Memory hotplug support for Xen balloon driver allows expanding memory
+	  available for the system above limit declared at system startup.
+	  It is very useful on critical systems which require long
+	  run without rebooting.
+
+	  Memory could be hotplugged in following steps:
+
+	    1) dom0: xl mem-max <domU> <maxmem>
+	       where <maxmem> is >= requested memory size,
+
+	    2) dom0: xl mem-set <domU> <memory>
+	       where <memory> is requested memory size; alternatively memory
+	       could be added by writing proper value to
+	       /sys/devices/system/xen_memory/xen_memory0/target or
+	       /sys/devices/system/xen_memory/xen_memory0/target_kb on dumU,
+
+	    3) domU: for i in /sys/devices/system/memory/memory*/state; do \
+	               [ "`cat "$i"`" = offline ] && echo online > "$i"; done
+
+	  Memory could be onlined automatically on domU by adding following line to udev rules:
+
+	  SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'"
+
+	  In that case step 3 should be omitted.
+
+config XEN_SCRUB_PAGES
+	bool "Scrub pages before returning them to system"
+	depends on XEN_BALLOON
+	default y
+	help
+	  Scrub pages before returning them to the system for reuse by
+	  other domains.  This makes sure that any confidential data
+	  is not accidentally visible to other domains.  Is it more
+	  secure, but slightly less efficient.
+	  If in doubt, say yes.
+
+config XEN_DEV_EVTCHN
+	tristate "Xen /dev/xen/evtchn device"
+	default y
+	help
+	  The evtchn driver allows a userspace process to triger event
+	  channels and to receive notification of an event channel
+	  firing.
+	  If in doubt, say yes.
+
+config XEN_BACKEND
+	bool "Backend driver support"
+	depends on XEN_DOM0
+	default y
+	help
+	  Support for backend device drivers that provide I/O services
+	  to other virtual machines.
+
+config XENFS
+	tristate "Xen filesystem"
+	select XEN_PRIVCMD
+	default y
+	help
+	  The xen filesystem provides a way for domains to share
+	  information with each other and with the hypervisor.
+	  For example, by reading and writing the "xenbus" file, guests
+	  may pass arbitrary information to the initial domain.
+	  If in doubt, say yes.
+
+config XEN_COMPAT_XENFS
+       bool "Create compatibility mount point /proc/xen"
+       depends on XENFS
+       default y
+       help
+         The old xenstore userspace tools expect to find "xenbus"
+         under /proc/xen, but "xenbus" is now found at the root of the
+         xenfs filesystem.  Selecting this causes the kernel to create
+         the compatibility mount point /proc/xen if it is running on
+         a xen platform.
+         If in doubt, say yes.
+
+config XEN_SYS_HYPERVISOR
+       bool "Create xen entries under /sys/hypervisor"
+       depends on SYSFS
+       select SYS_HYPERVISOR
+       default y
+       help
+         Create entries under /sys/hypervisor describing the Xen
+	 hypervisor environment.  When running native or in another
+	 virtual environment, /sys/hypervisor will still be present,
+	 but will have no xen contents.
+
+config XEN_XENBUS_FRONTEND
+	tristate
+
+config XEN_GNTDEV
+	tristate "userspace grant access device driver"
+	depends on XEN
+	default m
+	select MMU_NOTIFIER
+	help
+	  Allows userspace processes to use grants.
+
+config XEN_GRANT_DEV_ALLOC
+	tristate "User-space grant reference allocator driver"
+	depends on XEN
+	default m
+	help
+	  Allows userspace processes to create pages with access granted
+	  to other domains. This can be used to implement frontend drivers
+	  or as part of an inter-domain shared memory channel.
+
+config SWIOTLB_XEN
+	def_bool y
+	depends on PCI
+	select SWIOTLB
+
+config XEN_TMEM
+	bool
+	default y if (CLEANCACHE || FRONTSWAP)
+	help
+	  Shim to interface in-kernel Transcendent Memory hooks
+	  (e.g. cleancache and frontswap) to Xen tmem hypercalls.
+
+config XEN_PCIDEV_BACKEND
+	tristate "Xen PCI-device backend driver"
+	depends on PCI && X86 && XEN
+	depends on XEN_BACKEND
+	default m
+	help
+	  The PCI device backend driver allows the kernel to export arbitrary
+	  PCI devices to other guests. If you select this to be a module, you
+	  will need to make sure no other driver has bound to the device(s)
+	  you want to make visible to other guests.
+
+	  The parameter "passthrough" allows you specify how you want the PCI
+	  devices to appear in the guest. You can choose the default (0) where
+	  PCI topology starts at 00.00.0, or (1) for passthrough if you want
+	  the PCI devices topology appear the same as in the host.
+
+	  The "hide" parameter (only applicable if backend driver is compiled
+	  into the kernel) allows you to bind the PCI devices to this module
+	  from the default device drivers. The argument is the list of PCI BDFs:
+	  xen-pciback.hide=(03:00.0)(04:00.0)
+
+	  If in doubt, say m.
+
+config XEN_PRIVCMD
+	tristate
+	depends on XEN
+	default m
+
+config XEN_ACPI_PROCESSOR
+	tristate "Xen ACPI processor"
+	depends on XEN && X86 && ACPI_PROCESSOR && CPU_FREQ
+	default m
+	help
+          This ACPI processor uploads Power Management information to the Xen
+	  hypervisor.
+
+	  To do that the driver parses the Power Management data and uploads
+	  said information to the Xen hypervisor. Then the Xen hypervisor can
+	  select the proper Cx and Pxx states. It also registers itslef as the
+	  SMM so that other drivers (such as ACPI cpufreq scaling driver) will
+	  not load.
+
+          To compile this driver as a module, choose M here: the module will be
+	  called xen_acpi_processor  If you do not know what to choose, select
+	  M here. If the CPUFREQ drivers are built in, select Y here.
+
+endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
new file mode 100644
index 00000000..9adc5be5
--- /dev/null
+++ b/drivers/xen/Makefile
@@ -0,0 +1,27 @@
+obj-y	+= grant-table.o features.o events.o manage.o balloon.o
+obj-y	+= xenbus/
+
+nostackp := $(call cc-option, -fno-stack-protector)
+CFLAGS_features.o			:= $(nostackp)
+
+obj-$(CONFIG_BLOCK)			+= biomerge.o
+obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
+obj-$(CONFIG_XEN_XENCOMM)		+= xencomm.o
+obj-$(CONFIG_XEN_BALLOON)		+= xen-balloon.o
+obj-$(CONFIG_XEN_SELFBALLOONING)	+= xen-selfballoon.o
+obj-$(CONFIG_XEN_DEV_EVTCHN)		+= xen-evtchn.o
+obj-$(CONFIG_XEN_GNTDEV)		+= xen-gntdev.o
+obj-$(CONFIG_XEN_GRANT_DEV_ALLOC)	+= xen-gntalloc.o
+obj-$(CONFIG_XENFS)			+= xenfs/
+obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
+obj-$(CONFIG_XEN_PVHVM)			+= platform-pci.o
+obj-$(CONFIG_XEN_TMEM)			+= tmem.o
+obj-$(CONFIG_SWIOTLB_XEN)		+= swiotlb-xen.o
+obj-$(CONFIG_XEN_DOM0)			+= pci.o
+obj-$(CONFIG_XEN_PCIDEV_BACKEND)	+= xen-pciback/
+obj-$(CONFIG_XEN_PRIVCMD)		+= xen-privcmd.o
+obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o
+xen-evtchn-y				:= evtchn.o
+xen-gntdev-y				:= gntdev.o
+xen-gntalloc-y				:= gntalloc.o
+xen-privcmd-y				:= privcmd.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
new file mode 100644
index 00000000..31ab82fd
--- /dev/null
+++ b/drivers/xen/balloon.c
@@ -0,0 +1,627 @@
+/******************************************************************************
+ * Xen balloon driver - enables returning/claiming memory to/from Xen.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ *
+ * Memory hotplug support was written by Daniel Kiper. Work on
+ * it was sponsored by Google under Google Summer of Code 2010
+ * program. Jeremy Fitzhardinge from Citrix was the mentor for
+ * this project.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/gfp.h>
+#include <linux/notifier.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+#include <asm/e820.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/balloon.h>
+#include <xen/features.h>
+#include <xen/page.h>
+
+/*
+ * balloon_process() state:
+ *
+ * BP_DONE: done or nothing to do,
+ * BP_EAGAIN: error, go to sleep,
+ * BP_ECANCELED: error, balloon operation canceled.
+ */
+
+enum bp_state {
+	BP_DONE,
+	BP_EAGAIN,
+	BP_ECANCELED
+};
+
+
+static DEFINE_MUTEX(balloon_mutex);
+
+struct balloon_stats balloon_stats;
+EXPORT_SYMBOL_GPL(balloon_stats);
+
+/* We increase/decrease in batches which fit in a page */
+static unsigned long frame_list[PAGE_SIZE / sizeof(unsigned long)];
+
+#ifdef CONFIG_HIGHMEM
+#define inc_totalhigh_pages() (totalhigh_pages++)
+#define dec_totalhigh_pages() (totalhigh_pages--)
+#else
+#define inc_totalhigh_pages() do {} while (0)
+#define dec_totalhigh_pages() do {} while (0)
+#endif
+
+/* List of ballooned pages, threaded through the mem_map array. */
+static LIST_HEAD(ballooned_pages);
+
+/* Main work function, always executed in process context. */
+static void balloon_process(struct work_struct *work);
+static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
+
+/* When ballooning out (allocating memory to return to Xen) we don't really
+   want the kernel to try too hard since that can trigger the oom killer. */
+#define GFP_BALLOON \
+	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
+
+static void scrub_page(struct page *page)
+{
+#ifdef CONFIG_XEN_SCRUB_PAGES
+	clear_highpage(page);
+#endif
+}
+
+/* balloon_append: add the given page to the balloon. */
+static void __balloon_append(struct page *page)
+{
+	/* Lowmem is re-populated first, so highmem pages go at list tail. */
+	if (PageHighMem(page)) {
+		list_add_tail(&page->lru, &ballooned_pages);
+		balloon_stats.balloon_high++;
+	} else {
+		list_add(&page->lru, &ballooned_pages);
+		balloon_stats.balloon_low++;
+	}
+}
+
+static void balloon_append(struct page *page)
+{
+	__balloon_append(page);
+	if (PageHighMem(page))
+		dec_totalhigh_pages();
+	totalram_pages--;
+}
+
+/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
+static struct page *balloon_retrieve(bool prefer_highmem)
+{
+	struct page *page;
+
+	if (list_empty(&ballooned_pages))
+		return NULL;
+
+	if (prefer_highmem)
+		page = list_entry(ballooned_pages.prev, struct page, lru);
+	else
+		page = list_entry(ballooned_pages.next, struct page, lru);
+	list_del(&page->lru);
+
+	if (PageHighMem(page)) {
+		balloon_stats.balloon_high--;
+		inc_totalhigh_pages();
+	} else
+		balloon_stats.balloon_low--;
+
+	totalram_pages++;
+
+	return page;
+}
+
+static struct page *balloon_first_page(void)
+{
+	if (list_empty(&ballooned_pages))
+		return NULL;
+	return list_entry(ballooned_pages.next, struct page, lru);
+}
+
+static struct page *balloon_next_page(struct page *page)
+{
+	struct list_head *next = page->lru.next;
+	if (next == &ballooned_pages)
+		return NULL;
+	return list_entry(next, struct page, lru);
+}
+
+static enum bp_state update_schedule(enum bp_state state)
+{
+	if (state == BP_DONE) {
+		balloon_stats.schedule_delay = 1;
+		balloon_stats.retry_count = 1;
+		return BP_DONE;
+	}
+
+	++balloon_stats.retry_count;
+
+	if (balloon_stats.max_retry_count != RETRY_UNLIMITED &&
+			balloon_stats.retry_count > balloon_stats.max_retry_count) {
+		balloon_stats.schedule_delay = 1;
+		balloon_stats.retry_count = 1;
+		return BP_ECANCELED;
+	}
+
+	balloon_stats.schedule_delay <<= 1;
+
+	if (balloon_stats.schedule_delay > balloon_stats.max_schedule_delay)
+		balloon_stats.schedule_delay = balloon_stats.max_schedule_delay;
+
+	return BP_EAGAIN;
+}
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static long current_credit(void)
+{
+	return balloon_stats.target_pages - balloon_stats.current_pages -
+		balloon_stats.hotplug_pages;
+}
+
+static bool balloon_is_inflated(void)
+{
+	if (balloon_stats.balloon_low || balloon_stats.balloon_high ||
+			balloon_stats.balloon_hotplug)
+		return true;
+	else
+		return false;
+}
+
+/*
+ * reserve_additional_memory() adds memory region of size >= credit above
+ * max_pfn. New region is section aligned and size is modified to be multiple
+ * of section size. Those features allow optimal use of address space and
+ * establish proper alignment when this function is called first time after
+ * boot (last section not fully populated at boot time contains unused memory
+ * pages with PG_reserved bit not set; online_pages_range() does not allow page
+ * onlining in whole range if first onlined page does not have PG_reserved
+ * bit set). Real size of added memory is established at page onlining stage.
+ */
+
+static enum bp_state reserve_additional_memory(long credit)
+{
+	int nid, rc;
+	u64 hotplug_start_paddr;
+	unsigned long balloon_hotplug = credit;
+
+	hotplug_start_paddr = PFN_PHYS(SECTION_ALIGN_UP(max_pfn));
+	balloon_hotplug = round_up(balloon_hotplug, PAGES_PER_SECTION);
+	nid = memory_add_physaddr_to_nid(hotplug_start_paddr);
+
+	rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT);
+
+	if (rc) {
+		pr_info("xen_balloon: %s: add_memory() failed: %i\n", __func__, rc);
+		return BP_EAGAIN;
+	}
+
+	balloon_hotplug -= credit;
+
+	balloon_stats.hotplug_pages += credit;
+	balloon_stats.balloon_hotplug = balloon_hotplug;
+
+	return BP_DONE;
+}
+
+static void xen_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+
+	mutex_lock(&balloon_mutex);
+
+	__balloon_append(page);
+
+	if (balloon_stats.hotplug_pages)
+		--balloon_stats.hotplug_pages;
+	else
+		--balloon_stats.balloon_hotplug;
+
+	mutex_unlock(&balloon_mutex);
+}
+
+static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
+{
+	if (val == MEM_ONLINE)
+		schedule_delayed_work(&balloon_worker, 0);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_memory_nb = {
+	.notifier_call = xen_memory_notifier,
+	.priority = 0
+};
+#else
+static long current_credit(void)
+{
+	unsigned long target = balloon_stats.target_pages;
+
+	target = min(target,
+		     balloon_stats.current_pages +
+		     balloon_stats.balloon_low +
+		     balloon_stats.balloon_high);
+
+	return target - balloon_stats.current_pages;
+}
+
+static bool balloon_is_inflated(void)
+{
+	if (balloon_stats.balloon_low || balloon_stats.balloon_high)
+		return true;
+	else
+		return false;
+}
+
+static enum bp_state reserve_additional_memory(long credit)
+{
+	balloon_stats.target_pages = balloon_stats.current_pages;
+	return BP_DONE;
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
+
+static enum bp_state increase_reservation(unsigned long nr_pages)
+{
+	int rc;
+	unsigned long  pfn, i;
+	struct page   *page;
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = 0,
+		.domid        = DOMID_SELF
+	};
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	if (!balloon_stats.balloon_low && !balloon_stats.balloon_high) {
+		nr_pages = min(nr_pages, balloon_stats.balloon_hotplug);
+		balloon_stats.hotplug_pages += nr_pages;
+		balloon_stats.balloon_hotplug -= nr_pages;
+		return BP_DONE;
+	}
+#endif
+
+	if (nr_pages > ARRAY_SIZE(frame_list))
+		nr_pages = ARRAY_SIZE(frame_list);
+
+	page = balloon_first_page();
+	for (i = 0; i < nr_pages; i++) {
+		if (!page) {
+			nr_pages = i;
+			break;
+		}
+		frame_list[i] = page_to_pfn(page);
+		page = balloon_next_page(page);
+	}
+
+	set_xen_guest_handle(reservation.extent_start, frame_list);
+	reservation.nr_extents = nr_pages;
+	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+	if (rc <= 0)
+		return BP_EAGAIN;
+
+	for (i = 0; i < rc; i++) {
+		page = balloon_retrieve(false);
+		BUG_ON(page == NULL);
+
+		pfn = page_to_pfn(page);
+		BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
+		       phys_to_machine_mapping_valid(pfn));
+
+		set_phys_to_machine(pfn, frame_list[i]);
+
+		/* Link back into the page tables if not highmem. */
+		if (xen_pv_domain() && !PageHighMem(page)) {
+			int ret;
+			ret = HYPERVISOR_update_va_mapping(
+				(unsigned long)__va(pfn << PAGE_SHIFT),
+				mfn_pte(frame_list[i], PAGE_KERNEL),
+				0);
+			BUG_ON(ret);
+		}
+
+		/* Relinquish the page back to the allocator. */
+		ClearPageReserved(page);
+		init_page_count(page);
+		__free_page(page);
+	}
+
+	balloon_stats.current_pages += rc;
+
+	return BP_DONE;
+}
+
+static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
+{
+	enum bp_state state = BP_DONE;
+	unsigned long  pfn, i;
+	struct page   *page;
+	int ret;
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = 0,
+		.domid        = DOMID_SELF
+	};
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	if (balloon_stats.hotplug_pages) {
+		nr_pages = min(nr_pages, balloon_stats.hotplug_pages);
+		balloon_stats.hotplug_pages -= nr_pages;
+		balloon_stats.balloon_hotplug += nr_pages;
+		return BP_DONE;
+	}
+#endif
+
+	if (nr_pages > ARRAY_SIZE(frame_list))
+		nr_pages = ARRAY_SIZE(frame_list);
+
+	for (i = 0; i < nr_pages; i++) {
+		if ((page = alloc_page(gfp)) == NULL) {
+			nr_pages = i;
+			state = BP_EAGAIN;
+			break;
+		}
+
+		pfn = page_to_pfn(page);
+		frame_list[i] = pfn_to_mfn(pfn);
+
+		scrub_page(page);
+
+		if (xen_pv_domain() && !PageHighMem(page)) {
+			ret = HYPERVISOR_update_va_mapping(
+				(unsigned long)__va(pfn << PAGE_SHIFT),
+				__pte_ma(0), 0);
+			BUG_ON(ret);
+		}
+
+	}
+
+	/* Ensure that ballooned highmem pages don't have kmaps. */
+	kmap_flush_unused();
+	flush_tlb_all();
+
+	/* No more mappings: invalidate P2M and add to balloon. */
+	for (i = 0; i < nr_pages; i++) {
+		pfn = mfn_to_pfn(frame_list[i]);
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+		balloon_append(pfn_to_page(pfn));
+	}
+
+	set_xen_guest_handle(reservation.extent_start, frame_list);
+	reservation.nr_extents   = nr_pages;
+	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+	BUG_ON(ret != nr_pages);
+
+	balloon_stats.current_pages -= nr_pages;
+
+	return state;
+}
+
+/*
+ * We avoid multiple worker processes conflicting via the balloon mutex.
+ * We may of course race updates of the target counts (which are protected
+ * by the balloon lock), or with changes to the Xen hard limit, but we will
+ * recover from these in time.
+ */
+static void balloon_process(struct work_struct *work)
+{
+	enum bp_state state = BP_DONE;
+	long credit;
+
+	mutex_lock(&balloon_mutex);
+
+	do {
+		credit = current_credit();
+
+		if (credit > 0) {
+			if (balloon_is_inflated())
+				state = increase_reservation(credit);
+			else
+				state = reserve_additional_memory(credit);
+		}
+
+		if (credit < 0)
+			state = decrease_reservation(-credit, GFP_BALLOON);
+
+		state = update_schedule(state);
+
+#ifndef CONFIG_PREEMPT
+		if (need_resched())
+			schedule();
+#endif
+	} while (credit && state == BP_DONE);
+
+	/* Schedule more work if there is some still to be done. */
+	if (state == BP_EAGAIN)
+		schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
+
+	mutex_unlock(&balloon_mutex);
+}
+
+/* Resets the Xen limit, sets new target, and kicks off processing. */
+void balloon_set_new_target(unsigned long target)
+{
+	/* No need for lock. Not read-modify-write updates. */
+	balloon_stats.target_pages = target;
+	schedule_delayed_work(&balloon_worker, 0);
+}
+EXPORT_SYMBOL_GPL(balloon_set_new_target);
+
+/**
+ * alloc_xenballooned_pages - get pages that have been ballooned out
+ * @nr_pages: Number of pages to get
+ * @pages: pages returned
+ * @highmem: allow highmem pages
+ * @return 0 on success, error otherwise
+ */
+int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
+{
+	int pgno = 0;
+	struct page *page;
+	mutex_lock(&balloon_mutex);
+	while (pgno < nr_pages) {
+		page = balloon_retrieve(highmem);
+		if (page && (highmem || !PageHighMem(page))) {
+			pages[pgno++] = page;
+		} else {
+			enum bp_state st;
+			if (page)
+				balloon_append(page);
+			st = decrease_reservation(nr_pages - pgno,
+					highmem ? GFP_HIGHUSER : GFP_USER);
+			if (st != BP_DONE)
+				goto out_undo;
+		}
+	}
+	mutex_unlock(&balloon_mutex);
+	return 0;
+ out_undo:
+	while (pgno)
+		balloon_append(pages[--pgno]);
+	/* Free the memory back to the kernel soon */
+	schedule_delayed_work(&balloon_worker, 0);
+	mutex_unlock(&balloon_mutex);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(alloc_xenballooned_pages);
+
+/**
+ * free_xenballooned_pages - return pages retrieved with get_ballooned_pages
+ * @nr_pages: Number of pages
+ * @pages: pages to return
+ */
+void free_xenballooned_pages(int nr_pages, struct page **pages)
+{
+	int i;
+
+	mutex_lock(&balloon_mutex);
+
+	for (i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			balloon_append(pages[i]);
+	}
+
+	/* The balloon may be too large now. Shrink it if needed. */
+	if (current_credit())
+		schedule_delayed_work(&balloon_worker, 0);
+
+	mutex_unlock(&balloon_mutex);
+}
+EXPORT_SYMBOL(free_xenballooned_pages);
+
+static void __init balloon_add_region(unsigned long start_pfn,
+				      unsigned long pages)
+{
+	unsigned long pfn, extra_pfn_end;
+	struct page *page;
+
+	/*
+	 * If the amount of usable memory has been limited (e.g., with
+	 * the 'mem' command line parameter), don't add pages beyond
+	 * this limit.
+	 */
+	extra_pfn_end = min(max_pfn, start_pfn + pages);
+
+	for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
+		page = pfn_to_page(pfn);
+		/* totalram_pages and totalhigh_pages do not
+		   include the boot-time balloon extension, so
+		   don't subtract from it. */
+		__balloon_append(page);
+	}
+}
+
+static int __init balloon_init(void)
+{
+	int i;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	pr_info("xen/balloon: Initialising balloon driver.\n");
+
+	balloon_stats.current_pages = xen_pv_domain()
+		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
+		: max_pfn;
+	balloon_stats.target_pages  = balloon_stats.current_pages;
+	balloon_stats.balloon_low   = 0;
+	balloon_stats.balloon_high  = 0;
+
+	balloon_stats.schedule_delay = 1;
+	balloon_stats.max_schedule_delay = 32;
+	balloon_stats.retry_count = 1;
+	balloon_stats.max_retry_count = RETRY_UNLIMITED;
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	balloon_stats.hotplug_pages = 0;
+	balloon_stats.balloon_hotplug = 0;
+
+	set_online_page_callback(&xen_online_page);
+	register_memory_notifier(&xen_memory_nb);
+#endif
+
+	/*
+	 * Initialize the balloon with pages from the extra memory
+	 * regions (see arch/x86/xen/setup.c).
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
+		if (xen_extra_mem[i].size)
+			balloon_add_region(PFN_UP(xen_extra_mem[i].start),
+					   PFN_DOWN(xen_extra_mem[i].size));
+
+	return 0;
+}
+
+subsys_initcall(balloon_init);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
new file mode 100644
index 00000000..0edb91c0
--- /dev/null
+++ b/drivers/xen/biomerge.c
@@ -0,0 +1,15 @@
+#include <linux/bio.h>
+#include <linux/io.h>
+#include <linux/export.h>
+#include <xen/page.h>
+
+bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+			       const struct bio_vec *vec2)
+{
+	unsigned long mfn1 = pfn_to_mfn(page_to_pfn(vec1->bv_page));
+	unsigned long mfn2 = pfn_to_mfn(page_to_pfn(vec2->bv_page));
+
+	return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&
+		((mfn1 == mfn2) || ((mfn1+1) == mfn2));
+}
+EXPORT_SYMBOL(xen_biovec_phys_mergeable);
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
new file mode 100644
index 00000000..4dcfced1
--- /dev/null
+++ b/drivers/xen/cpu_hotplug.c
@@ -0,0 +1,112 @@
+#include <linux/notifier.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/cpu.h>
+
+static void enable_hotplug_cpu(int cpu)
+{
+	if (!cpu_present(cpu))
+		arch_register_cpu(cpu);
+
+	set_cpu_present(cpu, true);
+}
+
+static void disable_hotplug_cpu(int cpu)
+{
+	if (cpu_present(cpu))
+		arch_unregister_cpu(cpu);
+
+	set_cpu_present(cpu, false);
+}
+
+static int vcpu_online(unsigned int cpu)
+{
+	int err;
+	char dir[32], state[32];
+
+	sprintf(dir, "cpu/%u", cpu);
+	err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state);
+	if (err != 1) {
+		if (!xen_initial_domain())
+			printk(KERN_ERR "XENBUS: Unable to read cpu state\n");
+		return err;
+	}
+
+	if (strcmp(state, "online") == 0)
+		return 1;
+	else if (strcmp(state, "offline") == 0)
+		return 0;
+
+	printk(KERN_ERR "XENBUS: unknown state(%s) on CPU%d\n", state, cpu);
+	return -EINVAL;
+}
+static void vcpu_hotplug(unsigned int cpu)
+{
+	if (!cpu_possible(cpu))
+		return;
+
+	switch (vcpu_online(cpu)) {
+	case 1:
+		enable_hotplug_cpu(cpu);
+		break;
+	case 0:
+		(void)cpu_down(cpu);
+		disable_hotplug_cpu(cpu);
+		break;
+	default:
+		break;
+	}
+}
+
+static void handle_vcpu_hotplug_event(struct xenbus_watch *watch,
+					const char **vec, unsigned int len)
+{
+	unsigned int cpu;
+	char *cpustr;
+	const char *node = vec[XS_WATCH_PATH];
+
+	cpustr = strstr(node, "cpu/");
+	if (cpustr != NULL) {
+		sscanf(cpustr, "cpu/%u", &cpu);
+		vcpu_hotplug(cpu);
+	}
+}
+
+static int setup_cpu_watcher(struct notifier_block *notifier,
+			      unsigned long event, void *data)
+{
+	int cpu;
+	static struct xenbus_watch cpu_watch = {
+		.node = "cpu",
+		.callback = handle_vcpu_hotplug_event};
+
+	(void)register_xenbus_watch(&cpu_watch);
+
+	for_each_possible_cpu(cpu) {
+		if (vcpu_online(cpu) == 0) {
+			(void)cpu_down(cpu);
+			set_cpu_present(cpu, false);
+		}
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int __init setup_vcpu_hotplug_event(void)
+{
+	static struct notifier_block xsn_cpu = {
+		.notifier_call = setup_cpu_watcher };
+
+	if (!xen_pv_domain())
+		return -ENODEV;
+
+	register_xenstore_notifier(&xsn_cpu);
+
+	return 0;
+}
+
+arch_initcall(setup_vcpu_hotplug_event);
+
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
new file mode 100644
index 00000000..6908e4ce
--- /dev/null
+++ b/drivers/xen/events.c
@@ -0,0 +1,1817 @@
+/*
+ * Xen event channels
+ *
+ * Xen models interrupts with abstract event channels.  Because each
+ * domain gets 1024 event channels, but NR_IRQ is not that large, we
+ * must dynamically map irqs<->event channels.  The event channels
+ * interface with the rest of the kernel by defining a xen interrupt
+ * chip.  When an event is received, it is mapped to an irq and sent
+ * through the normal interrupt processing path.
+ *
+ * There are four kinds of events which can be mapped to an event
+ * channel:
+ *
+ * 1. Inter-domain notifications.  This includes all the virtual
+ *    device events, since they're driven by front-ends in another domain
+ *    (typically dom0).
+ * 2. VIRQs, typically used for timers.  These are per-cpu events.
+ * 3. IPIs.
+ * 4. PIRQs - Hardware interrupts.
+ *
+ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
+ */
+
+#include <linux/linkage.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+#include <linux/irqnr.h>
+#include <linux/pci.h>
+
+#include <asm/desc.h>
+#include <asm/ptrace.h>
+#include <asm/irq.h>
+#include <asm/idle.h>
+#include <asm/io_apic.h>
+#include <asm/sync_bitops.h>
+#include <asm/xen/page.h>
+#include <asm/xen/pci.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
+#include <xen/hvm.h>
+#include <xen/xen-ops.h>
+#include <xen/events.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/event_channel.h>
+#include <xen/interface/hvm/hvm_op.h>
+#include <xen/interface/hvm/params.h>
+
+/*
+ * This lock protects updates to the following mapping and reference-count
+ * arrays. The lock does not need to be acquired to read the mapping tables.
+ */
+static DEFINE_MUTEX(irq_mapping_update_lock);
+
+static LIST_HEAD(xen_irq_list_head);
+
+/* IRQ <-> VIRQ mapping. */
+static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
+
+/* IRQ <-> IPI mapping */
+static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
+
+/* Interrupt types. */
+enum xen_irq_type {
+	IRQT_UNBOUND = 0,
+	IRQT_PIRQ,
+	IRQT_VIRQ,
+	IRQT_IPI,
+	IRQT_EVTCHN
+};
+
+/*
+ * Packed IRQ information:
+ * type - enum xen_irq_type
+ * event channel - irq->event channel mapping
+ * cpu - cpu this event channel is bound to
+ * index - type-specific information:
+ *    PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM
+ *           guest, or GSI (real passthrough IRQ) of the device.
+ *    VIRQ - virq number
+ *    IPI - IPI vector
+ *    EVTCHN -
+ */
+struct irq_info {
+	struct list_head list;
+	int refcnt;
+	enum xen_irq_type type;	/* type */
+	unsigned irq;
+	unsigned short evtchn;	/* event channel */
+	unsigned short cpu;	/* cpu bound */
+
+	union {
+		unsigned short virq;
+		enum ipi_vector ipi;
+		struct {
+			unsigned short pirq;
+			unsigned short gsi;
+			unsigned char vector;
+			unsigned char flags;
+			uint16_t domid;
+		} pirq;
+	} u;
+};
+#define PIRQ_NEEDS_EOI	(1 << 0)
+#define PIRQ_SHAREABLE	(1 << 1)
+
+static int *evtchn_to_irq;
+static unsigned long *pirq_eoi_map;
+static bool (*pirq_needs_eoi)(unsigned irq);
+
+static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
+		      cpu_evtchn_mask);
+
+/* Xen will never allocate port zero for any purpose. */
+#define VALID_EVTCHN(chn)	((chn) != 0)
+
+static struct irq_chip xen_dynamic_chip;
+static struct irq_chip xen_percpu_chip;
+static struct irq_chip xen_pirq_chip;
+static void enable_dynirq(struct irq_data *data);
+static void disable_dynirq(struct irq_data *data);
+
+/* Get info for IRQ */
+static struct irq_info *info_for_irq(unsigned irq)
+{
+	return irq_get_handler_data(irq);
+}
+
+/* Constructors for packed IRQ information. */
+static void xen_irq_info_common_init(struct irq_info *info,
+				     unsigned irq,
+				     enum xen_irq_type type,
+				     unsigned short evtchn,
+				     unsigned short cpu)
+{
+
+	BUG_ON(info->type != IRQT_UNBOUND && info->type != type);
+
+	info->type = type;
+	info->irq = irq;
+	info->evtchn = evtchn;
+	info->cpu = cpu;
+
+	evtchn_to_irq[evtchn] = irq;
+}
+
+static void xen_irq_info_evtchn_init(unsigned irq,
+				     unsigned short evtchn)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
+}
+
+static void xen_irq_info_ipi_init(unsigned cpu,
+				  unsigned irq,
+				  unsigned short evtchn,
+				  enum ipi_vector ipi)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	xen_irq_info_common_init(info, irq, IRQT_IPI, evtchn, 0);
+
+	info->u.ipi = ipi;
+
+	per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+}
+
+static void xen_irq_info_virq_init(unsigned cpu,
+				   unsigned irq,
+				   unsigned short evtchn,
+				   unsigned short virq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	xen_irq_info_common_init(info, irq, IRQT_VIRQ, evtchn, 0);
+
+	info->u.virq = virq;
+
+	per_cpu(virq_to_irq, cpu)[virq] = irq;
+}
+
+static void xen_irq_info_pirq_init(unsigned irq,
+				   unsigned short evtchn,
+				   unsigned short pirq,
+				   unsigned short gsi,
+				   unsigned short vector,
+				   uint16_t domid,
+				   unsigned char flags)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	xen_irq_info_common_init(info, irq, IRQT_PIRQ, evtchn, 0);
+
+	info->u.pirq.pirq = pirq;
+	info->u.pirq.gsi = gsi;
+	info->u.pirq.vector = vector;
+	info->u.pirq.domid = domid;
+	info->u.pirq.flags = flags;
+}
+
+/*
+ * Accessors for packed IRQ information.
+ */
+static unsigned int evtchn_from_irq(unsigned irq)
+{
+	if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq)))
+		return 0;
+
+	return info_for_irq(irq)->evtchn;
+}
+
+unsigned irq_from_evtchn(unsigned int evtchn)
+{
+	return evtchn_to_irq[evtchn];
+}
+EXPORT_SYMBOL_GPL(irq_from_evtchn);
+
+static enum ipi_vector ipi_from_irq(unsigned irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info == NULL);
+	BUG_ON(info->type != IRQT_IPI);
+
+	return info->u.ipi;
+}
+
+static unsigned virq_from_irq(unsigned irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info == NULL);
+	BUG_ON(info->type != IRQT_VIRQ);
+
+	return info->u.virq;
+}
+
+static unsigned pirq_from_irq(unsigned irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info == NULL);
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	return info->u.pirq.pirq;
+}
+
+static enum xen_irq_type type_from_irq(unsigned irq)
+{
+	return info_for_irq(irq)->type;
+}
+
+static unsigned cpu_from_irq(unsigned irq)
+{
+	return info_for_irq(irq)->cpu;
+}
+
+static unsigned int cpu_from_evtchn(unsigned int evtchn)
+{
+	int irq = evtchn_to_irq[evtchn];
+	unsigned ret = 0;
+
+	if (irq != -1)
+		ret = cpu_from_irq(irq);
+
+	return ret;
+}
+
+static bool pirq_check_eoi_map(unsigned irq)
+{
+	return test_bit(pirq_from_irq(irq), pirq_eoi_map);
+}
+
+static bool pirq_needs_eoi_flag(unsigned irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
+}
+
+static inline unsigned long active_evtchns(unsigned int cpu,
+					   struct shared_info *sh,
+					   unsigned int idx)
+{
+	return sh->evtchn_pending[idx] &
+		per_cpu(cpu_evtchn_mask, cpu)[idx] &
+		~sh->evtchn_mask[idx];
+}
+
+static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
+{
+	int irq = evtchn_to_irq[chn];
+
+	BUG_ON(irq == -1);
+#ifdef CONFIG_SMP
+	cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
+#endif
+
+	clear_bit(chn, per_cpu(cpu_evtchn_mask, cpu_from_irq(irq)));
+	set_bit(chn, per_cpu(cpu_evtchn_mask, cpu));
+
+	info_for_irq(irq)->cpu = cpu;
+}
+
+static void init_evtchn_cpu_bindings(void)
+{
+	int i;
+#ifdef CONFIG_SMP
+	struct irq_info *info;
+
+	/* By default all event channels notify CPU#0. */
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		struct irq_desc *desc = irq_to_desc(info->irq);
+		cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
+	}
+#endif
+
+	for_each_possible_cpu(i)
+		memset(per_cpu(cpu_evtchn_mask, i),
+		       (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
+}
+
+static inline void clear_evtchn(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	sync_clear_bit(port, &s->evtchn_pending[0]);
+}
+
+static inline void set_evtchn(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	sync_set_bit(port, &s->evtchn_pending[0]);
+}
+
+static inline int test_evtchn(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	return sync_test_bit(port, &s->evtchn_pending[0]);
+}
+
+
+/**
+ * notify_remote_via_irq - send event to remote end of event channel via irq
+ * @irq: irq of event channel to send event to
+ *
+ * Unlike notify_remote_via_evtchn(), this is safe to use across
+ * save/restore. Notifications on a broken connection are silently
+ * dropped.
+ */
+void notify_remote_via_irq(int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+
+	if (VALID_EVTCHN(evtchn))
+		notify_remote_via_evtchn(evtchn);
+}
+EXPORT_SYMBOL_GPL(notify_remote_via_irq);
+
+static void mask_evtchn(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	sync_set_bit(port, &s->evtchn_mask[0]);
+}
+
+static void unmask_evtchn(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	unsigned int cpu = get_cpu();
+
+	BUG_ON(!irqs_disabled());
+
+	/* Slow path (hypercall) if this is a non-local port. */
+	if (unlikely(cpu != cpu_from_evtchn(port))) {
+		struct evtchn_unmask unmask = { .port = port };
+		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
+	} else {
+		struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
+
+		sync_clear_bit(port, &s->evtchn_mask[0]);
+
+		/*
+		 * The following is basically the equivalent of
+		 * 'hw_resend_irq'. Just like a real IO-APIC we 'lose
+		 * the interrupt edge' if the channel is masked.
+		 */
+		if (sync_test_bit(port, &s->evtchn_pending[0]) &&
+		    !sync_test_and_set_bit(port / BITS_PER_LONG,
+					   &vcpu_info->evtchn_pending_sel))
+			vcpu_info->evtchn_upcall_pending = 1;
+	}
+
+	put_cpu();
+}
+
+static void xen_irq_init(unsigned irq)
+{
+	struct irq_info *info;
+#ifdef CONFIG_SMP
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	/* By default all event channels notify CPU#0. */
+	cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
+#endif
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (info == NULL)
+		panic("Unable to allocate metadata for IRQ%d\n", irq);
+
+	info->type = IRQT_UNBOUND;
+	info->refcnt = -1;
+
+	irq_set_handler_data(irq, info);
+
+	list_add_tail(&info->list, &xen_irq_list_head);
+}
+
+static int __must_check xen_allocate_irq_dynamic(void)
+{
+	int first = 0;
+	int irq;
+
+#ifdef CONFIG_X86_IO_APIC
+	/*
+	 * For an HVM guest or domain 0 which see "real" (emulated or
+	 * actual respectively) GSIs we allocate dynamic IRQs
+	 * e.g. those corresponding to event channels or MSIs
+	 * etc. from the range above those "real" GSIs to avoid
+	 * collisions.
+	 */
+	if (xen_initial_domain() || xen_hvm_domain())
+		first = get_nr_irqs_gsi();
+#endif
+
+	irq = irq_alloc_desc_from(first, -1);
+
+	if (irq >= 0)
+		xen_irq_init(irq);
+
+	return irq;
+}
+
+static int __must_check xen_allocate_irq_gsi(unsigned gsi)
+{
+	int irq;
+
+	/*
+	 * A PV guest has no concept of a GSI (since it has no ACPI
+	 * nor access to/knowledge of the physical APICs). Therefore
+	 * all IRQs are dynamically allocated from the entire IRQ
+	 * space.
+	 */
+	if (xen_pv_domain() && !xen_initial_domain())
+		return xen_allocate_irq_dynamic();
+
+	/* Legacy IRQ descriptors are already allocated by the arch. */
+	if (gsi < NR_IRQS_LEGACY)
+		irq = gsi;
+	else
+		irq = irq_alloc_desc_at(gsi, -1);
+
+	xen_irq_init(irq);
+
+	return irq;
+}
+
+static void xen_free_irq(unsigned irq)
+{
+	struct irq_info *info = irq_get_handler_data(irq);
+
+	list_del(&info->list);
+
+	irq_set_handler_data(irq, NULL);
+
+	WARN_ON(info->refcnt > 0);
+
+	kfree(info);
+
+	/* Legacy IRQ descriptors are managed by the arch. */
+	if (irq < NR_IRQS_LEGACY)
+		return;
+
+	irq_free_desc(irq);
+}
+
+static void pirq_query_unmask(int irq)
+{
+	struct physdev_irq_status_query irq_status;
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	irq_status.irq = pirq_from_irq(irq);
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+		irq_status.flags = 0;
+
+	info->u.pirq.flags &= ~PIRQ_NEEDS_EOI;
+	if (irq_status.flags & XENIRQSTAT_needs_eoi)
+		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
+}
+
+static bool probing_irq(int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return desc && desc->action == NULL;
+}
+
+static void eoi_pirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+	int rc = 0;
+
+	irq_move_irq(data);
+
+	if (VALID_EVTCHN(evtchn))
+		clear_evtchn(evtchn);
+
+	if (pirq_needs_eoi(data->irq)) {
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+		WARN_ON(rc);
+	}
+}
+
+static void mask_ack_pirq(struct irq_data *data)
+{
+	disable_dynirq(data);
+	eoi_pirq(data);
+}
+
+static unsigned int __startup_pirq(unsigned int irq)
+{
+	struct evtchn_bind_pirq bind_pirq;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = evtchn_from_irq(irq);
+	int rc;
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	if (VALID_EVTCHN(evtchn))
+		goto out;
+
+	bind_pirq.pirq = pirq_from_irq(irq);
+	/* NB. We are happy to share unless we are probing. */
+	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
+					BIND_PIRQ__WILL_SHARE : 0;
+	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
+	if (rc != 0) {
+		if (!probing_irq(irq))
+			printk(KERN_INFO "Failed to obtain physical IRQ %d\n",
+			       irq);
+		return 0;
+	}
+	evtchn = bind_pirq.port;
+
+	pirq_query_unmask(irq);
+
+	evtchn_to_irq[evtchn] = irq;
+	bind_evtchn_to_cpu(evtchn, 0);
+	info->evtchn = evtchn;
+
+out:
+	unmask_evtchn(evtchn);
+	eoi_pirq(irq_get_irq_data(irq));
+
+	return 0;
+}
+
+static unsigned int startup_pirq(struct irq_data *data)
+{
+	return __startup_pirq(data->irq);
+}
+
+static void shutdown_pirq(struct irq_data *data)
+{
+	struct evtchn_close close;
+	unsigned int irq = data->irq;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = evtchn_from_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	if (!VALID_EVTCHN(evtchn))
+		return;
+
+	mask_evtchn(evtchn);
+
+	close.port = evtchn;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+
+	bind_evtchn_to_cpu(evtchn, 0);
+	evtchn_to_irq[evtchn] = -1;
+	info->evtchn = 0;
+}
+
+static void enable_pirq(struct irq_data *data)
+{
+	startup_pirq(data);
+}
+
+static void disable_pirq(struct irq_data *data)
+{
+	disable_dynirq(data);
+}
+
+int xen_irq_from_gsi(unsigned gsi)
+{
+	struct irq_info *info;
+
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		if (info->type != IRQT_PIRQ)
+			continue;
+
+		if (info->u.pirq.gsi == gsi)
+			return info->irq;
+	}
+
+	return -1;
+}
+EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
+
+/*
+ * Do not make any assumptions regarding the relationship between the
+ * IRQ number returned here and the Xen pirq argument.
+ *
+ * Note: We don't assign an event channel until the irq actually started
+ * up.  Return an existing irq if we've already got one for the gsi.
+ *
+ * Shareable implies level triggered, not shareable implies edge
+ * triggered here.
+ */
+int xen_bind_pirq_gsi_to_irq(unsigned gsi,
+			     unsigned pirq, int shareable, char *name)
+{
+	int irq = -1;
+	struct physdev_irq irq_op;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = xen_irq_from_gsi(gsi);
+	if (irq != -1) {
+		printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
+		       irq, gsi);
+		goto out;
+	}
+
+	irq = xen_allocate_irq_gsi(gsi);
+	if (irq < 0)
+		goto out;
+
+	irq_op.irq = irq;
+	irq_op.vector = 0;
+
+	/* Only the privileged domain can do this. For non-priv, the pcifront
+	 * driver provides a PCI bus that does the call to do exactly
+	 * this in the priv domain. */
+	if (xen_initial_domain() &&
+	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
+		xen_free_irq(irq);
+		irq = -ENOSPC;
+		goto out;
+	}
+
+	xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
+			       shareable ? PIRQ_SHAREABLE : 0);
+
+	pirq_query_unmask(irq);
+	/* We try to use the handler with the appropriate semantic for the
+	 * type of interrupt: if the interrupt is an edge triggered
+	 * interrupt we use handle_edge_irq.
+	 *
+	 * On the other hand if the interrupt is level triggered we use
+	 * handle_fasteoi_irq like the native code does for this kind of
+	 * interrupts.
+	 *
+	 * Depending on the Xen version, pirq_needs_eoi might return true
+	 * not only for level triggered interrupts but for edge triggered
+	 * interrupts too. In any case Xen always honors the eoi mechanism,
+	 * not injecting any more pirqs of the same kind if the first one
+	 * hasn't received an eoi yet. Therefore using the fasteoi handler
+	 * is the right choice either way.
+	 */
+	if (shareable)
+		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+				handle_fasteoi_irq, name);
+	else
+		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+				handle_edge_irq, name);
+
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return irq;
+}
+
+#ifdef CONFIG_PCI_MSI
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
+{
+	int rc;
+	struct physdev_get_free_pirq op_get_free_pirq;
+
+	op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
+
+	WARN_ONCE(rc == -ENOSYS,
+		  "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
+
+	return rc ? -1 : op_get_free_pirq.pirq;
+}
+
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			     int pirq, int vector, const char *name,
+			     domid_t domid)
+{
+	int irq, ret;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = xen_allocate_irq_dynamic();
+	if (irq < 0)
+		goto out;
+
+	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
+			name);
+
+	xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
+	ret = irq_set_msi_desc(irq, msidesc);
+	if (ret < 0)
+		goto error_irq;
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+	return irq;
+error_irq:
+	mutex_unlock(&irq_mapping_update_lock);
+	xen_free_irq(irq);
+	return ret;
+}
+#endif
+
+int xen_destroy_irq(int irq)
+{
+	struct irq_desc *desc;
+	struct physdev_unmap_pirq unmap_irq;
+	struct irq_info *info = info_for_irq(irq);
+	int rc = -ENOENT;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	desc = irq_to_desc(irq);
+	if (!desc)
+		goto out;
+
+	if (xen_initial_domain()) {
+		unmap_irq.pirq = info->u.pirq.pirq;
+		unmap_irq.domid = info->u.pirq.domid;
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
+		/* If another domain quits without making the pci_disable_msix
+		 * call, the Xen hypervisor takes care of freeing the PIRQs
+		 * (free_domain_pirqs).
+		 */
+		if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
+			printk(KERN_INFO "domain %d does not have %d anymore\n",
+				info->u.pirq.domid, info->u.pirq.pirq);
+		else if (rc) {
+			printk(KERN_WARNING "unmap irq failed %d\n", rc);
+			goto out;
+		}
+	}
+
+	xen_free_irq(irq);
+
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+	return rc;
+}
+
+int xen_irq_from_pirq(unsigned pirq)
+{
+	int irq;
+
+	struct irq_info *info;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		if (info->type != IRQT_PIRQ)
+			continue;
+		irq = info->irq;
+		if (info->u.pirq.pirq == pirq)
+			goto out;
+	}
+	irq = -1;
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return irq;
+}
+
+
+int xen_pirq_from_irq(unsigned irq)
+{
+	return pirq_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
+int bind_evtchn_to_irq(unsigned int evtchn)
+{
+	int irq;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = evtchn_to_irq[evtchn];
+
+	if (irq == -1) {
+		irq = xen_allocate_irq_dynamic();
+		if (irq == -1)
+			goto out;
+
+		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+					      handle_edge_irq, "event");
+
+		xen_irq_info_evtchn_init(irq, evtchn);
+	}
+
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return irq;
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
+
+static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
+{
+	struct evtchn_bind_ipi bind_ipi;
+	int evtchn, irq;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = per_cpu(ipi_to_irq, cpu)[ipi];
+
+	if (irq == -1) {
+		irq = xen_allocate_irq_dynamic();
+		if (irq < 0)
+			goto out;
+
+		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+					      handle_percpu_irq, "ipi");
+
+		bind_ipi.vcpu = cpu;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
+						&bind_ipi) != 0)
+			BUG();
+		evtchn = bind_ipi.port;
+
+		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
+
+		bind_evtchn_to_cpu(evtchn, cpu);
+	}
+
+ out:
+	mutex_unlock(&irq_mapping_update_lock);
+	return irq;
+}
+
+static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+					  unsigned int remote_port)
+{
+	struct evtchn_bind_interdomain bind_interdomain;
+	int err;
+
+	bind_interdomain.remote_dom  = remote_domain;
+	bind_interdomain.remote_port = remote_port;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+					  &bind_interdomain);
+
+	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+}
+
+static int find_virq(unsigned int virq, unsigned int cpu)
+{
+	struct evtchn_status status;
+	int port, rc = -ENOENT;
+
+	memset(&status, 0, sizeof(status));
+	for (port = 0; port <= NR_EVENT_CHANNELS; port++) {
+		status.dom = DOMID_SELF;
+		status.port = port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
+		if (rc < 0)
+			continue;
+		if (status.status != EVTCHNSTAT_virq)
+			continue;
+		if (status.u.virq == virq && status.vcpu == cpu) {
+			rc = port;
+			break;
+		}
+	}
+	return rc;
+}
+
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
+{
+	struct evtchn_bind_virq bind_virq;
+	int evtchn, irq, ret;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = per_cpu(virq_to_irq, cpu)[virq];
+
+	if (irq == -1) {
+		irq = xen_allocate_irq_dynamic();
+		if (irq == -1)
+			goto out;
+
+		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+					      handle_percpu_irq, "virq");
+
+		bind_virq.virq = virq;
+		bind_virq.vcpu = cpu;
+		ret = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						&bind_virq);
+		if (ret == 0)
+			evtchn = bind_virq.port;
+		else {
+			if (ret == -EEXIST)
+				ret = find_virq(virq, cpu);
+			BUG_ON(ret < 0);
+			evtchn = ret;
+		}
+
+		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
+
+		bind_evtchn_to_cpu(evtchn, cpu);
+	}
+
+out:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return irq;
+}
+
+static void unbind_from_irq(unsigned int irq)
+{
+	struct evtchn_close close;
+	int evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = irq_get_handler_data(irq);
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	if (info->refcnt > 0) {
+		info->refcnt--;
+		if (info->refcnt != 0)
+			goto done;
+	}
+
+	if (VALID_EVTCHN(evtchn)) {
+		close.port = evtchn;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+			BUG();
+
+		switch (type_from_irq(irq)) {
+		case IRQT_VIRQ:
+			per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
+				[virq_from_irq(irq)] = -1;
+			break;
+		case IRQT_IPI:
+			per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
+				[ipi_from_irq(irq)] = -1;
+			break;
+		default:
+			break;
+		}
+
+		/* Closed ports are implicitly re-bound to VCPU0. */
+		bind_evtchn_to_cpu(evtchn, 0);
+
+		evtchn_to_irq[evtchn] = -1;
+	}
+
+	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
+
+	xen_free_irq(irq);
+
+ done:
+	mutex_unlock(&irq_mapping_update_lock);
+}
+
+int bind_evtchn_to_irqhandler(unsigned int evtchn,
+			      irq_handler_t handler,
+			      unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	int irq, retval;
+
+	irq = bind_evtchn_to_irq(evtchn);
+	if (irq < 0)
+		return irq;
+	retval = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (retval != 0) {
+		unbind_from_irq(irq);
+		return retval;
+	}
+
+	return irq;
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
+
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  unsigned int remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id)
+{
+	int irq, retval;
+
+	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+	if (irq < 0)
+		return irq;
+
+	retval = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (retval != 0) {
+		unbind_from_irq(irq);
+		return retval;
+	}
+
+	return irq;
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
+
+int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
+			    irq_handler_t handler,
+			    unsigned long irqflags, const char *devname, void *dev_id)
+{
+	int irq, retval;
+
+	irq = bind_virq_to_irq(virq, cpu);
+	if (irq < 0)
+		return irq;
+	retval = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (retval != 0) {
+		unbind_from_irq(irq);
+		return retval;
+	}
+
+	return irq;
+}
+EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);
+
+int bind_ipi_to_irqhandler(enum ipi_vector ipi,
+			   unsigned int cpu,
+			   irq_handler_t handler,
+			   unsigned long irqflags,
+			   const char *devname,
+			   void *dev_id)
+{
+	int irq, retval;
+
+	irq = bind_ipi_to_irq(ipi, cpu);
+	if (irq < 0)
+		return irq;
+
+	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME | IRQF_EARLY_RESUME;
+	retval = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (retval != 0) {
+		unbind_from_irq(irq);
+		return retval;
+	}
+
+	return irq;
+}
+
+void unbind_from_irqhandler(unsigned int irq, void *dev_id)
+{
+	free_irq(irq, dev_id);
+	unbind_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
+
+int evtchn_make_refcounted(unsigned int evtchn)
+{
+	int irq = evtchn_to_irq[evtchn];
+	struct irq_info *info;
+
+	if (irq == -1)
+		return -ENOENT;
+
+	info = irq_get_handler_data(irq);
+
+	if (!info)
+		return -ENOENT;
+
+	WARN_ON(info->refcnt != -1);
+
+	info->refcnt = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(evtchn_make_refcounted);
+
+int evtchn_get(unsigned int evtchn)
+{
+	int irq;
+	struct irq_info *info;
+	int err = -ENOENT;
+
+	if (evtchn >= NR_EVENT_CHANNELS)
+		return -EINVAL;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = evtchn_to_irq[evtchn];
+	if (irq == -1)
+		goto done;
+
+	info = irq_get_handler_data(irq);
+
+	if (!info)
+		goto done;
+
+	err = -EINVAL;
+	if (info->refcnt <= 0)
+		goto done;
+
+	info->refcnt++;
+	err = 0;
+ done:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(evtchn_get);
+
+void evtchn_put(unsigned int evtchn)
+{
+	int irq = evtchn_to_irq[evtchn];
+	if (WARN_ON(irq == -1))
+		return;
+	unbind_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(evtchn_put);
+
+void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
+{
+	int irq = per_cpu(ipi_to_irq, cpu)[vector];
+	BUG_ON(irq < 0);
+	notify_remote_via_irq(irq);
+}
+
+irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
+{
+	struct shared_info *sh = HYPERVISOR_shared_info;
+	int cpu = smp_processor_id();
+	unsigned long *cpu_evtchn = per_cpu(cpu_evtchn_mask, cpu);
+	int i;
+	unsigned long flags;
+	static DEFINE_SPINLOCK(debug_lock);
+	struct vcpu_info *v;
+
+	spin_lock_irqsave(&debug_lock, flags);
+
+	printk("\nvcpu %d\n  ", cpu);
+
+	for_each_online_cpu(i) {
+		int pending;
+		v = per_cpu(xen_vcpu, i);
+		pending = (get_irq_regs() && i == cpu)
+			? xen_irqs_disabled(get_irq_regs())
+			: v->evtchn_upcall_mask;
+		printk("%d: masked=%d pending=%d event_sel %0*lx\n  ", i,
+		       pending, v->evtchn_upcall_pending,
+		       (int)(sizeof(v->evtchn_pending_sel)*2),
+		       v->evtchn_pending_sel);
+	}
+	v = per_cpu(xen_vcpu, cpu);
+
+	printk("\npending:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2,
+		       sh->evtchn_pending[i],
+		       i % 8 == 0 ? "\n   " : " ");
+	printk("\nglobal mask:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
+		printk("%0*lx%s",
+		       (int)(sizeof(sh->evtchn_mask[0])*2),
+		       sh->evtchn_mask[i],
+		       i % 8 == 0 ? "\n   " : " ");
+
+	printk("\nglobally unmasked:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
+		       sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
+		       i % 8 == 0 ? "\n   " : " ");
+
+	printk("\nlocal cpu%d mask:\n   ", cpu);
+	for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2),
+		       cpu_evtchn[i],
+		       i % 8 == 0 ? "\n   " : " ");
+
+	printk("\nlocally unmasked:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) {
+		unsigned long pending = sh->evtchn_pending[i]
+			& ~sh->evtchn_mask[i]
+			& cpu_evtchn[i];
+		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
+		       pending, i % 8 == 0 ? "\n   " : " ");
+	}
+
+	printk("\npending list:\n");
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+		if (sync_test_bit(i, sh->evtchn_pending)) {
+			int word_idx = i / BITS_PER_LONG;
+			printk("  %d: event %d -> irq %d%s%s%s\n",
+			       cpu_from_evtchn(i), i,
+			       evtchn_to_irq[i],
+			       sync_test_bit(word_idx, &v->evtchn_pending_sel)
+					     ? "" : " l2-clear",
+			       !sync_test_bit(i, sh->evtchn_mask)
+					     ? "" : " globally-masked",
+			       sync_test_bit(i, cpu_evtchn)
+					     ? "" : " locally-masked");
+		}
+	}
+
+	spin_unlock_irqrestore(&debug_lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static DEFINE_PER_CPU(unsigned, xed_nesting_count);
+static DEFINE_PER_CPU(unsigned int, current_word_idx);
+static DEFINE_PER_CPU(unsigned int, current_bit_idx);
+
+/*
+ * Mask out the i least significant bits of w
+ */
+#define MASK_LSBS(w, i) (w & ((~0UL) << i))
+
+/*
+ * Search the CPUs pending events bitmasks.  For each one found, map
+ * the event number to an irq, and feed it into do_IRQ() for
+ * handling.
+ *
+ * Xen uses a two-level bitmap to speed searching.  The first level is
+ * a bitset of words which contain pending event bits.  The second
+ * level is a bitset of pending events themselves.
+ */
+static void __xen_evtchn_do_upcall(void)
+{
+	int start_word_idx, start_bit_idx;
+	int word_idx, bit_idx;
+	int i;
+	int cpu = get_cpu();
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
+	unsigned count;
+
+	do {
+		unsigned long pending_words;
+
+		vcpu_info->evtchn_upcall_pending = 0;
+
+		if (__this_cpu_inc_return(xed_nesting_count) - 1)
+			goto out;
+
+#ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
+		/* Clear master flag /before/ clearing selector flag. */
+		wmb();
+#endif
+		pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
+
+		start_word_idx = __this_cpu_read(current_word_idx);
+		start_bit_idx = __this_cpu_read(current_bit_idx);
+
+		word_idx = start_word_idx;
+
+		for (i = 0; pending_words != 0; i++) {
+			unsigned long pending_bits;
+			unsigned long words;
+
+			words = MASK_LSBS(pending_words, word_idx);
+
+			/*
+			 * If we masked out all events, wrap to beginning.
+			 */
+			if (words == 0) {
+				word_idx = 0;
+				bit_idx = 0;
+				continue;
+			}
+			word_idx = __ffs(words);
+
+			pending_bits = active_evtchns(cpu, s, word_idx);
+			bit_idx = 0; /* usually scan entire word from start */
+			if (word_idx == start_word_idx) {
+				/* We scan the starting word in two parts */
+				if (i == 0)
+					/* 1st time: start in the middle */
+					bit_idx = start_bit_idx;
+				else
+					/* 2nd time: mask bits done already */
+					bit_idx &= (1UL << start_bit_idx) - 1;
+			}
+
+			do {
+				unsigned long bits;
+				int port, irq;
+				struct irq_desc *desc;
+
+				bits = MASK_LSBS(pending_bits, bit_idx);
+
+				/* If we masked out all events, move on. */
+				if (bits == 0)
+					break;
+
+				bit_idx = __ffs(bits);
+
+				/* Process port. */
+				port = (word_idx * BITS_PER_LONG) + bit_idx;
+				irq = evtchn_to_irq[port];
+
+				if (irq != -1) {
+					desc = irq_to_desc(irq);
+					if (desc)
+						generic_handle_irq_desc(irq, desc);
+				}
+
+				bit_idx = (bit_idx + 1) % BITS_PER_LONG;
+
+				/* Next caller starts at last processed + 1 */
+				__this_cpu_write(current_word_idx,
+						 bit_idx ? word_idx :
+						 (word_idx+1) % BITS_PER_LONG);
+				__this_cpu_write(current_bit_idx, bit_idx);
+			} while (bit_idx != 0);
+
+			/* Scan start_l1i twice; all others once. */
+			if ((word_idx != start_word_idx) || (i != 0))
+				pending_words &= ~(1UL << word_idx);
+
+			word_idx = (word_idx + 1) % BITS_PER_LONG;
+		}
+
+		BUG_ON(!irqs_disabled());
+
+		count = __this_cpu_read(xed_nesting_count);
+		__this_cpu_write(xed_nesting_count, 0);
+	} while (count != 1 || vcpu_info->evtchn_upcall_pending);
+
+out:
+
+	put_cpu();
+}
+
+void xen_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	exit_idle();
+	irq_enter();
+
+	__xen_evtchn_do_upcall();
+
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+void xen_hvm_evtchn_do_upcall(void)
+{
+	__xen_evtchn_do_upcall();
+}
+EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall);
+
+/* Rebind a new event channel to an existing irq. */
+void rebind_evtchn_irq(int evtchn, int irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	/* Make sure the irq is masked, since the new event channel
+	   will also be masked. */
+	disable_irq(irq);
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	/* After resume the irq<->evtchn mappings are all cleared out */
+	BUG_ON(evtchn_to_irq[evtchn] != -1);
+	/* Expect irq to have been bound before,
+	   so there should be a proper type */
+	BUG_ON(info->type == IRQT_UNBOUND);
+
+	xen_irq_info_evtchn_init(irq, evtchn);
+
+	mutex_unlock(&irq_mapping_update_lock);
+
+	/* new event channels are always bound to cpu 0 */
+	irq_set_affinity(irq, cpumask_of(0));
+
+	/* Unmask the event channel. */
+	enable_irq(irq);
+}
+
+/* Rebind an evtchn so that it gets delivered to a specific cpu */
+static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
+{
+	struct evtchn_bind_vcpu bind_vcpu;
+	int evtchn = evtchn_from_irq(irq);
+
+	if (!VALID_EVTCHN(evtchn))
+		return -1;
+
+	/*
+	 * Events delivered via platform PCI interrupts are always
+	 * routed to vcpu 0 and hence cannot be rebound.
+	 */
+	if (xen_hvm_domain() && !xen_have_vector_callback)
+		return -1;
+
+	/* Send future instances of this interrupt to other vcpu. */
+	bind_vcpu.port = evtchn;
+	bind_vcpu.vcpu = tcpu;
+
+	/*
+	 * If this fails, it usually just indicates that we're dealing with a
+	 * virq or IPI channel, which don't actually need to be rebound. Ignore
+	 * it, but don't do the xenlinux-level rebind in that case.
+	 */
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
+		bind_evtchn_to_cpu(evtchn, tcpu);
+
+	return 0;
+}
+
+static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
+			    bool force)
+{
+	unsigned tcpu = cpumask_first(dest);
+
+	return rebind_irq_to_cpu(data->irq, tcpu);
+}
+
+int resend_irq_on_evtchn(unsigned int irq)
+{
+	int masked, evtchn = evtchn_from_irq(irq);
+	struct shared_info *s = HYPERVISOR_shared_info;
+
+	if (!VALID_EVTCHN(evtchn))
+		return 1;
+
+	masked = sync_test_and_set_bit(evtchn, s->evtchn_mask);
+	sync_set_bit(evtchn, s->evtchn_pending);
+	if (!masked)
+		unmask_evtchn(evtchn);
+
+	return 1;
+}
+
+static void enable_dynirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+
+	if (VALID_EVTCHN(evtchn))
+		unmask_evtchn(evtchn);
+}
+
+static void disable_dynirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+
+	if (VALID_EVTCHN(evtchn))
+		mask_evtchn(evtchn);
+}
+
+static void ack_dynirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+
+	irq_move_irq(data);
+
+	if (VALID_EVTCHN(evtchn))
+		clear_evtchn(evtchn);
+}
+
+static void mask_ack_dynirq(struct irq_data *data)
+{
+	disable_dynirq(data);
+	ack_dynirq(data);
+}
+
+static int retrigger_dynirq(struct irq_data *data)
+{
+	int evtchn = evtchn_from_irq(data->irq);
+	struct shared_info *sh = HYPERVISOR_shared_info;
+	int ret = 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		int masked;
+
+		masked = sync_test_and_set_bit(evtchn, sh->evtchn_mask);
+		sync_set_bit(evtchn, sh->evtchn_pending);
+		if (!masked)
+			unmask_evtchn(evtchn);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+static void restore_pirqs(void)
+{
+	int pirq, rc, irq, gsi;
+	struct physdev_map_pirq map_irq;
+	struct irq_info *info;
+
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		if (info->type != IRQT_PIRQ)
+			continue;
+
+		pirq = info->u.pirq.pirq;
+		gsi = info->u.pirq.gsi;
+		irq = info->irq;
+
+		/* save/restore of PT devices doesn't work, so at this point the
+		 * only devices present are GSI based emulated devices */
+		if (!gsi)
+			continue;
+
+		map_irq.domid = DOMID_SELF;
+		map_irq.type = MAP_PIRQ_TYPE_GSI;
+		map_irq.index = gsi;
+		map_irq.pirq = pirq;
+
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+		if (rc) {
+			printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
+					gsi, irq, pirq, rc);
+			xen_free_irq(irq);
+			continue;
+		}
+
+		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
+
+		__startup_pirq(irq);
+	}
+}
+
+static void restore_cpu_virqs(unsigned int cpu)
+{
+	struct evtchn_bind_virq bind_virq;
+	int virq, irq, evtchn;
+
+	for (virq = 0; virq < NR_VIRQS; virq++) {
+		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
+			continue;
+
+		BUG_ON(virq_from_irq(irq) != virq);
+
+		/* Get a new binding from Xen. */
+		bind_virq.virq = virq;
+		bind_virq.vcpu = cpu;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						&bind_virq) != 0)
+			BUG();
+		evtchn = bind_virq.port;
+
+		/* Record the new mapping. */
+		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
+		bind_evtchn_to_cpu(evtchn, cpu);
+	}
+}
+
+static void restore_cpu_ipis(unsigned int cpu)
+{
+	struct evtchn_bind_ipi bind_ipi;
+	int ipi, irq, evtchn;
+
+	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
+		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
+			continue;
+
+		BUG_ON(ipi_from_irq(irq) != ipi);
+
+		/* Get a new binding from Xen. */
+		bind_ipi.vcpu = cpu;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
+						&bind_ipi) != 0)
+			BUG();
+		evtchn = bind_ipi.port;
+
+		/* Record the new mapping. */
+		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
+		bind_evtchn_to_cpu(evtchn, cpu);
+	}
+}
+
+/* Clear an irq's pending state, in preparation for polling on it */
+void xen_clear_irq_pending(int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+
+	if (VALID_EVTCHN(evtchn))
+		clear_evtchn(evtchn);
+}
+EXPORT_SYMBOL(xen_clear_irq_pending);
+void xen_set_irq_pending(int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+
+	if (VALID_EVTCHN(evtchn))
+		set_evtchn(evtchn);
+}
+
+bool xen_test_irq_pending(int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+	bool ret = false;
+
+	if (VALID_EVTCHN(evtchn))
+		ret = test_evtchn(evtchn);
+
+	return ret;
+}
+
+/* Poll waiting for an irq to become pending with timeout.  In the usual case,
+ * the irq will be disabled so it won't deliver an interrupt. */
+void xen_poll_irq_timeout(int irq, u64 timeout)
+{
+	evtchn_port_t evtchn = evtchn_from_irq(irq);
+
+	if (VALID_EVTCHN(evtchn)) {
+		struct sched_poll poll;
+
+		poll.nr_ports = 1;
+		poll.timeout = timeout;
+		set_xen_guest_handle(poll.ports, &evtchn);
+
+		if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
+			BUG();
+	}
+}
+EXPORT_SYMBOL(xen_poll_irq_timeout);
+/* Poll waiting for an irq to become pending.  In the usual case, the
+ * irq will be disabled so it won't deliver an interrupt. */
+void xen_poll_irq(int irq)
+{
+	xen_poll_irq_timeout(irq, 0 /* no timeout */);
+}
+
+/* Check whether the IRQ line is shared with other guests. */
+int xen_test_irq_shared(int irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+	struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
+
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+		return 0;
+	return !(irq_status.flags & XENIRQSTAT_shared);
+}
+EXPORT_SYMBOL_GPL(xen_test_irq_shared);
+
+void xen_irq_resume(void)
+{
+	unsigned int cpu, evtchn;
+	struct irq_info *info;
+
+	init_evtchn_cpu_bindings();
+
+	/* New event-channel space is not 'live' yet. */
+	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
+		mask_evtchn(evtchn);
+
+	/* No IRQ <-> event-channel mappings. */
+	list_for_each_entry(info, &xen_irq_list_head, list)
+		info->evtchn = 0; /* zap event-channel binding */
+
+	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
+		evtchn_to_irq[evtchn] = -1;
+
+	for_each_possible_cpu(cpu) {
+		restore_cpu_virqs(cpu);
+		restore_cpu_ipis(cpu);
+	}
+
+	restore_pirqs();
+}
+
+static struct irq_chip xen_dynamic_chip __read_mostly = {
+	.name			= "xen-dyn",
+
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= ack_dynirq,
+	.irq_mask_ack		= mask_ack_dynirq,
+
+	.irq_set_affinity	= set_affinity_irq,
+	.irq_retrigger		= retrigger_dynirq,
+};
+
+static struct irq_chip xen_pirq_chip __read_mostly = {
+	.name			= "xen-pirq",
+
+	.irq_startup		= startup_pirq,
+	.irq_shutdown		= shutdown_pirq,
+	.irq_enable		= enable_pirq,
+	.irq_disable		= disable_pirq,
+
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= eoi_pirq,
+	.irq_eoi		= eoi_pirq,
+	.irq_mask_ack		= mask_ack_pirq,
+
+	.irq_set_affinity	= set_affinity_irq,
+
+	.irq_retrigger		= retrigger_dynirq,
+};
+
+static struct irq_chip xen_percpu_chip __read_mostly = {
+	.name			= "xen-percpu",
+
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= ack_dynirq,
+};
+
+int xen_set_callback_via(uint64_t via)
+{
+	struct xen_hvm_param a;
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+	a.value = via;
+	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
+#ifdef CONFIG_XEN_PVHVM
+/* Vector callbacks are better than PCI interrupts to receive event
+ * channel notifications because we can receive vector callbacks on any
+ * vcpu and we don't need PCI support or APIC interactions. */
+void xen_callback_vector(void)
+{
+	int rc;
+	uint64_t callback_via;
+	if (xen_have_vector_callback) {
+		callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK);
+		rc = xen_set_callback_via(callback_via);
+		if (rc) {
+			printk(KERN_ERR "Request for Xen HVM callback vector"
+					" failed.\n");
+			xen_have_vector_callback = 0;
+			return;
+		}
+		printk(KERN_INFO "Xen HVM callback vector for event delivery is "
+				"enabled\n");
+		/* in the restore case the vector has already been allocated */
+		if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors))
+			alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector);
+	}
+}
+#else
+void xen_callback_vector(void) {}
+#endif
+
+void __init xen_init_IRQ(void)
+{
+	int i, rc;
+
+	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
+				    GFP_KERNEL);
+	BUG_ON(!evtchn_to_irq);
+	for (i = 0; i < NR_EVENT_CHANNELS; i++)
+		evtchn_to_irq[i] = -1;
+
+	init_evtchn_cpu_bindings();
+
+	/* No event channels are 'live' right now. */
+	for (i = 0; i < NR_EVENT_CHANNELS; i++)
+		mask_evtchn(i);
+
+	pirq_needs_eoi = pirq_needs_eoi_flag;
+
+	if (xen_hvm_domain()) {
+		xen_callback_vector();
+		native_init_IRQ();
+		/* pci_xen_hvm_init must be called after native_init_IRQ so that
+		 * __acpi_register_gsi can point at the right function */
+		pci_xen_hvm_init();
+	} else {
+		struct physdev_pirq_eoi_gmfn eoi_gmfn;
+
+		irq_ctx_init(smp_processor_id());
+		if (xen_initial_domain())
+			pci_xen_initial_domain();
+
+		pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+		eoi_gmfn.gmfn = virt_to_mfn(pirq_eoi_map);
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn);
+		if (rc != 0) {
+			free_page((unsigned long) pirq_eoi_map);
+			pirq_eoi_map = NULL;
+		} else
+			pirq_needs_eoi = pirq_check_eoi_map;
+	}
+}
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
new file mode 100644
index 00000000..b1f60a0c
--- /dev/null
+++ b/drivers/xen/evtchn.c
@@ -0,0 +1,560 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+	struct mutex bind_mutex; /* serialize bind/unbind operations */
+
+	/* Notification ring, accessed via /dev/xen/evtchn. */
+#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
+#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+	evtchn_port_t *ring;
+	unsigned int ring_cons, ring_prod, ring_overflow;
+	struct mutex ring_cons_mutex; /* protect against concurrent readers */
+
+	/* Processes wait on this queue when ring is empty. */
+	wait_queue_head_t evtchn_wait;
+	struct fasync_struct *evtchn_async_queue;
+	const char *name;
+};
+
+/*
+ * Who's bound to each port?  This is logically an array of struct
+ * per_user_data *, but we encode the current enabled-state in bit 0.
+ */
+static unsigned long *port_user;
+static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+
+static inline struct per_user_data *get_port_user(unsigned port)
+{
+	return (struct per_user_data *)(port_user[port] & ~1);
+}
+
+static inline void set_port_user(unsigned port, struct per_user_data *u)
+{
+	port_user[port] = (unsigned long)u;
+}
+
+static inline bool get_port_enabled(unsigned port)
+{
+	return port_user[port] & 1;
+}
+
+static inline void set_port_enabled(unsigned port, bool enabled)
+{
+	if (enabled)
+		port_user[port] |= 1;
+	else
+		port_user[port] &= ~1;
+}
+
+static irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+	unsigned int port = (unsigned long)data;
+	struct per_user_data *u;
+
+	spin_lock(&port_user_lock);
+
+	u = get_port_user(port);
+
+	WARN(!get_port_enabled(port),
+	     "Interrupt for port %d, but apparently not enabled; per-user %p\n",
+	     port, u);
+
+	disable_irq_nosync(irq);
+	set_port_enabled(port, false);
+
+	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
+		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+		wmb(); /* Ensure ring contents visible */
+		if (u->ring_cons == u->ring_prod++) {
+			wake_up_interruptible(&u->evtchn_wait);
+			kill_fasync(&u->evtchn_async_queue,
+				    SIGIO, POLL_IN);
+		}
+	} else
+		u->ring_overflow = 1;
+
+	spin_unlock(&port_user_lock);
+
+	return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	int rc;
+	unsigned int c, p, bytes1 = 0, bytes2 = 0;
+	struct per_user_data *u = file->private_data;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	if (count == 0)
+		return 0;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	for (;;) {
+		mutex_lock(&u->ring_cons_mutex);
+
+		rc = -EFBIG;
+		if (u->ring_overflow)
+			goto unlock_out;
+
+		c = u->ring_cons;
+		p = u->ring_prod;
+		if (c != p)
+			break;
+
+		mutex_unlock(&u->ring_cons_mutex);
+
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		rc = wait_event_interruptible(u->evtchn_wait,
+					      u->ring_cons != u->ring_prod);
+		if (rc)
+			return rc;
+	}
+
+	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+	if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
+		bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+			sizeof(evtchn_port_t);
+		bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+	} else {
+		bytes1 = (p - c) * sizeof(evtchn_port_t);
+		bytes2 = 0;
+	}
+
+	/* Truncate chunks according to caller's maximum byte count. */
+	if (bytes1 > count) {
+		bytes1 = count;
+		bytes2 = 0;
+	} else if ((bytes1 + bytes2) > count) {
+		bytes2 = count - bytes1;
+	}
+
+	rc = -EFAULT;
+	rmb(); /* Ensure that we see the port before we copy it. */
+	if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+	    ((bytes2 != 0) &&
+	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+		goto unlock_out;
+
+	u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
+	rc = bytes1 + bytes2;
+
+ unlock_out:
+	mutex_unlock(&u->ring_cons_mutex);
+	return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	int rc, i;
+	evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	struct per_user_data *u = file->private_data;
+
+	if (kbuf == NULL)
+		return -ENOMEM;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	rc = 0;
+	if (count == 0)
+		goto out;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	rc = -EFAULT;
+	if (copy_from_user(kbuf, buf, count) != 0)
+		goto out;
+
+	spin_lock_irq(&port_user_lock);
+
+	for (i = 0; i < (count/sizeof(evtchn_port_t)); i++) {
+		unsigned port = kbuf[i];
+
+		if (port < NR_EVENT_CHANNELS &&
+		    get_port_user(port) == u &&
+		    !get_port_enabled(port)) {
+			set_port_enabled(port, true);
+			enable_irq(irq_from_evtchn(port));
+		}
+	}
+
+	spin_unlock_irq(&port_user_lock);
+
+	rc = count;
+
+ out:
+	free_page((unsigned long)kbuf);
+	return rc;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, int port)
+{
+	int rc = 0;
+
+	/*
+	 * Ports are never reused, so every caller should pass in a
+	 * unique port.
+	 *
+	 * (Locking not necessary because we haven't registered the
+	 * interrupt handler yet, and our caller has already
+	 * serialized bind operations.)
+	 */
+	BUG_ON(get_port_user(port) != NULL);
+	set_port_user(port, u);
+	set_port_enabled(port, true); /* start enabled */
+
+	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+				       u->name, (void *)(unsigned long)port);
+	if (rc >= 0)
+		rc = evtchn_make_refcounted(port);
+
+	return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+{
+	int irq = irq_from_evtchn(port);
+
+	unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+
+	set_port_user(port, NULL);
+}
+
+static long evtchn_ioctl(struct file *file,
+			 unsigned int cmd, unsigned long arg)
+{
+	int rc;
+	struct per_user_data *u = file->private_data;
+	void __user *uarg = (void __user *) arg;
+
+	/* Prevent bind from racing with unbind */
+	mutex_lock(&u->bind_mutex);
+
+	switch (cmd) {
+	case IOCTL_EVTCHN_BIND_VIRQ: {
+		struct ioctl_evtchn_bind_virq bind;
+		struct evtchn_bind_virq bind_virq;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_virq.virq = bind.virq;
+		bind_virq.vcpu = 0;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						 &bind_virq);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_virq.port);
+		if (rc == 0)
+			rc = bind_virq.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+		struct ioctl_evtchn_bind_interdomain bind;
+		struct evtchn_bind_interdomain bind_interdomain;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_interdomain.remote_dom  = bind.remote_domain;
+		bind_interdomain.remote_port = bind.remote_port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+						 &bind_interdomain);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+		if (rc == 0)
+			rc = bind_interdomain.local_port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+		struct ioctl_evtchn_bind_unbound_port bind;
+		struct evtchn_alloc_unbound alloc_unbound;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		alloc_unbound.dom        = DOMID_SELF;
+		alloc_unbound.remote_dom = bind.remote_domain;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+						 &alloc_unbound);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, alloc_unbound.port);
+		if (rc == 0)
+			rc = alloc_unbound.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_UNBIND: {
+		struct ioctl_evtchn_unbind unbind;
+
+		rc = -EFAULT;
+		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+			break;
+
+		rc = -EINVAL;
+		if (unbind.port >= NR_EVENT_CHANNELS)
+			break;
+
+		spin_lock_irq(&port_user_lock);
+
+		rc = -ENOTCONN;
+		if (get_port_user(unbind.port) != u) {
+			spin_unlock_irq(&port_user_lock);
+			break;
+		}
+
+		disable_irq(irq_from_evtchn(unbind.port));
+
+		spin_unlock_irq(&port_user_lock);
+
+		evtchn_unbind_from_user(u, unbind.port);
+
+		rc = 0;
+		break;
+	}
+
+	case IOCTL_EVTCHN_NOTIFY: {
+		struct ioctl_evtchn_notify notify;
+
+		rc = -EFAULT;
+		if (copy_from_user(&notify, uarg, sizeof(notify)))
+			break;
+
+		if (notify.port >= NR_EVENT_CHANNELS) {
+			rc = -EINVAL;
+		} else if (get_port_user(notify.port) != u) {
+			rc = -ENOTCONN;
+		} else {
+			notify_remote_via_evtchn(notify.port);
+			rc = 0;
+		}
+		break;
+	}
+
+	case IOCTL_EVTCHN_RESET: {
+		/* Initialise the ring to empty. Clear errors. */
+		mutex_lock(&u->ring_cons_mutex);
+		spin_lock_irq(&port_user_lock);
+		u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+		spin_unlock_irq(&port_user_lock);
+		mutex_unlock(&u->ring_cons_mutex);
+		rc = 0;
+		break;
+	}
+
+	default:
+		rc = -ENOSYS;
+		break;
+	}
+	mutex_unlock(&u->bind_mutex);
+
+	return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+	unsigned int mask = POLLOUT | POLLWRNORM;
+	struct per_user_data *u = file->private_data;
+
+	poll_wait(file, &u->evtchn_wait, wait);
+	if (u->ring_cons != u->ring_prod)
+		mask |= POLLIN | POLLRDNORM;
+	if (u->ring_overflow)
+		mask = POLLERR;
+	return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+	struct per_user_data *u = filp->private_data;
+	return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+	struct per_user_data *u;
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+	if (u->name == NULL) {
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	init_waitqueue_head(&u->evtchn_wait);
+
+	u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	if (u->ring == NULL) {
+		kfree(u->name);
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	mutex_init(&u->bind_mutex);
+	mutex_init(&u->ring_cons_mutex);
+
+	filp->private_data = u;
+
+	return nonseekable_open(inode, filp);
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+	int i;
+	struct per_user_data *u = filp->private_data;
+
+	spin_lock_irq(&port_user_lock);
+
+	free_page((unsigned long)u->ring);
+
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+		if (get_port_user(i) != u)
+			continue;
+
+		disable_irq(irq_from_evtchn(i));
+	}
+
+	spin_unlock_irq(&port_user_lock);
+
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+		if (get_port_user(i) != u)
+			continue;
+
+		evtchn_unbind_from_user(get_port_user(i), i);
+	}
+
+	kfree(u->name);
+	kfree(u);
+
+	return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+	.owner   = THIS_MODULE,
+	.read    = evtchn_read,
+	.write   = evtchn_write,
+	.unlocked_ioctl = evtchn_ioctl,
+	.poll    = evtchn_poll,
+	.fasync  = evtchn_fasync,
+	.open    = evtchn_open,
+	.release = evtchn_release,
+	.llseek	 = no_llseek,
+};
+
+static struct miscdevice evtchn_miscdev = {
+	.minor        = MISC_DYNAMIC_MINOR,
+	.name         = "xen/evtchn",
+	.fops         = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	port_user = kcalloc(NR_EVENT_CHANNELS, sizeof(*port_user), GFP_KERNEL);
+	if (port_user == NULL)
+		return -ENOMEM;
+
+	spin_lock_init(&port_user_lock);
+
+	/* Create '/dev/misc/evtchn'. */
+	err = misc_register(&evtchn_miscdev);
+	if (err != 0) {
+		printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+		return err;
+	}
+
+	printk(KERN_INFO "Event-channel device installed.\n");
+
+	return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+	kfree(port_user);
+	port_user = NULL;
+
+	misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/features.c b/drivers/xen/features.c
new file mode 100644
index 00000000..99eda169
--- /dev/null
+++ b/drivers/xen/features.c
@@ -0,0 +1,33 @@
+/******************************************************************************
+ * features.c
+ *
+ * Xen feature flags.
+ *
+ * Copyright (c) 2006, Ian Campbell, XenSource Inc.
+ */
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <linux/module.h>
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+#include <xen/features.h>
+
+u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly;
+EXPORT_SYMBOL_GPL(xen_features);
+
+void xen_setup_features(void)
+{
+	struct xen_feature_info fi;
+	int i, j;
+
+	for (i = 0; i < XENFEAT_NR_SUBMAPS; i++) {
+		fi.submap_idx = i;
+		if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0)
+			break;
+		for (j = 0; j < 32; j++)
+			xen_features[i * 32 + j] = !!(fi.submap & 1<<j);
+	}
+}
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
new file mode 100644
index 00000000..934985d1
--- /dev/null
+++ b/drivers/xen/gntalloc.c
@@ -0,0 +1,608 @@
+/******************************************************************************
+ * gntalloc.c
+ *
+ * Device for creating grant references (in user-space) that may be shared
+ * with other domains.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+/*
+ * This driver exists to allow userspace programs in Linux to allocate kernel
+ * memory that will later be shared with another domain.  Without this device,
+ * Linux userspace programs cannot create grant references.
+ *
+ * How this stuff works:
+ *   X -> granting a page to Y
+ *   Y -> mapping the grant from X
+ *
+ *   1. X uses the gntalloc device to allocate a page of kernel memory, P.
+ *   2. X creates an entry in the grant table that says domid(Y) can access P.
+ *      This is done without a hypercall unless the grant table needs expansion.
+ *   3. X gives the grant reference identifier, GREF, to Y.
+ *   4. Y maps the page, either directly into kernel memory for use in a backend
+ *      driver, or via a the gntdev device to map into the address space of an
+ *      application running in Y. This is the first point at which Xen does any
+ *      tracking of the page.
+ *   5. A program in X mmap()s a segment of the gntalloc device that corresponds
+ *      to the shared page, and can now communicate with Y over the shared page.
+ *
+ *
+ * NOTE TO USERSPACE LIBRARIES:
+ *   The grant allocation and mmap()ing are, naturally, two separate operations.
+ *   You set up the sharing by calling the create ioctl() and then the mmap().
+ *   Teardown requires munmap() and either close() or ioctl().
+ *
+ * WARNING: Since Xen does not allow a guest to forcibly end the use of a grant
+ * reference, this device can be used to consume kernel memory by leaving grant
+ * references mapped by another domain when an application exits. Therefore,
+ * there is a global limit on the number of pages that can be allocated. When
+ * all references to the page are unmapped, it will be freed during the next
+ * grant operation.
+ */
+
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/highmem.h>
+
+#include <xen/xen.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+#include <xen/gntalloc.h>
+#include <xen/events.h>
+
+static int limit = 1024;
+module_param(limit, int, 0644);
+MODULE_PARM_DESC(limit, "Maximum number of grants that may be allocated by "
+		"the gntalloc device");
+
+static LIST_HEAD(gref_list);
+static DEFINE_MUTEX(gref_mutex);
+static int gref_size;
+
+struct notify_info {
+	uint16_t pgoff:12;    /* Bits 0-11: Offset of the byte to clear */
+	uint16_t flags:2;     /* Bits 12-13: Unmap notification flags */
+	int event;            /* Port (event channel) to notify */
+};
+
+/* Metadata on a grant reference. */
+struct gntalloc_gref {
+	struct list_head next_gref;  /* list entry gref_list */
+	struct list_head next_file;  /* list entry file->list, if open */
+	struct page *page;	     /* The shared page */
+	uint64_t file_index;         /* File offset for mmap() */
+	unsigned int users;          /* Use count - when zero, waiting on Xen */
+	grant_ref_t gref_id;         /* The grant reference number */
+	struct notify_info notify;   /* Unmap notification */
+};
+
+struct gntalloc_file_private_data {
+	struct list_head list;
+	uint64_t index;
+};
+
+struct gntalloc_vma_private_data {
+	struct gntalloc_gref *gref;
+	int users;
+	int count;
+};
+
+static void __del_gref(struct gntalloc_gref *gref);
+
+static void do_cleanup(void)
+{
+	struct gntalloc_gref *gref, *n;
+	list_for_each_entry_safe(gref, n, &gref_list, next_gref) {
+		if (!gref->users)
+			__del_gref(gref);
+	}
+}
+
+static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
+	uint32_t *gref_ids, struct gntalloc_file_private_data *priv)
+{
+	int i, rc, readonly;
+	LIST_HEAD(queue_gref);
+	LIST_HEAD(queue_file);
+	struct gntalloc_gref *gref;
+
+	readonly = !(op->flags & GNTALLOC_FLAG_WRITABLE);
+	rc = -ENOMEM;
+	for (i = 0; i < op->count; i++) {
+		gref = kzalloc(sizeof(*gref), GFP_KERNEL);
+		if (!gref)
+			goto undo;
+		list_add_tail(&gref->next_gref, &queue_gref);
+		list_add_tail(&gref->next_file, &queue_file);
+		gref->users = 1;
+		gref->file_index = op->index + i * PAGE_SIZE;
+		gref->page = alloc_page(GFP_KERNEL|__GFP_ZERO);
+		if (!gref->page)
+			goto undo;
+
+		/* Grant foreign access to the page. */
+		gref->gref_id = gnttab_grant_foreign_access(op->domid,
+			pfn_to_mfn(page_to_pfn(gref->page)), readonly);
+		if ((int)gref->gref_id < 0) {
+			rc = gref->gref_id;
+			goto undo;
+		}
+		gref_ids[i] = gref->gref_id;
+	}
+
+	/* Add to gref lists. */
+	mutex_lock(&gref_mutex);
+	list_splice_tail(&queue_gref, &gref_list);
+	list_splice_tail(&queue_file, &priv->list);
+	mutex_unlock(&gref_mutex);
+
+	return 0;
+
+undo:
+	mutex_lock(&gref_mutex);
+	gref_size -= (op->count - i);
+
+	list_for_each_entry(gref, &queue_file, next_file) {
+		/* __del_gref does not remove from queue_file */
+		__del_gref(gref);
+	}
+
+	/* It's possible for the target domain to map the just-allocated grant
+	 * references by blindly guessing their IDs; if this is done, then
+	 * __del_gref will leave them in the queue_gref list. They need to be
+	 * added to the global list so that we can free them when they are no
+	 * longer referenced.
+	 */
+	if (unlikely(!list_empty(&queue_gref)))
+		list_splice_tail(&queue_gref, &gref_list);
+	mutex_unlock(&gref_mutex);
+	return rc;
+}
+
+static void __del_gref(struct gntalloc_gref *gref)
+{
+	if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
+		uint8_t *tmp = kmap(gref->page);
+		tmp[gref->notify.pgoff] = 0;
+		kunmap(gref->page);
+	}
+	if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
+		notify_remote_via_evtchn(gref->notify.event);
+		evtchn_put(gref->notify.event);
+	}
+
+	gref->notify.flags = 0;
+
+	if (gref->gref_id > 0) {
+		if (gnttab_query_foreign_access(gref->gref_id))
+			return;
+
+		if (!gnttab_end_foreign_access_ref(gref->gref_id, 0))
+			return;
+
+		gnttab_free_grant_reference(gref->gref_id);
+	}
+
+	gref_size--;
+	list_del(&gref->next_gref);
+
+	if (gref->page)
+		__free_page(gref->page);
+
+	kfree(gref);
+}
+
+/* finds contiguous grant references in a file, returns the first */
+static struct gntalloc_gref *find_grefs(struct gntalloc_file_private_data *priv,
+		uint64_t index, uint32_t count)
+{
+	struct gntalloc_gref *rv = NULL, *gref;
+	list_for_each_entry(gref, &priv->list, next_file) {
+		if (gref->file_index == index && !rv)
+			rv = gref;
+		if (rv) {
+			if (gref->file_index != index)
+				return NULL;
+			index += PAGE_SIZE;
+			count--;
+			if (count == 0)
+				return rv;
+		}
+	}
+	return NULL;
+}
+
+/*
+ * -------------------------------------
+ *  File operations.
+ * -------------------------------------
+ */
+static int gntalloc_open(struct inode *inode, struct file *filp)
+{
+	struct gntalloc_file_private_data *priv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		goto out_nomem;
+	INIT_LIST_HEAD(&priv->list);
+
+	filp->private_data = priv;
+
+	pr_debug("%s: priv %p\n", __func__, priv);
+
+	return 0;
+
+out_nomem:
+	return -ENOMEM;
+}
+
+static int gntalloc_release(struct inode *inode, struct file *filp)
+{
+	struct gntalloc_file_private_data *priv = filp->private_data;
+	struct gntalloc_gref *gref;
+
+	pr_debug("%s: priv %p\n", __func__, priv);
+
+	mutex_lock(&gref_mutex);
+	while (!list_empty(&priv->list)) {
+		gref = list_entry(priv->list.next,
+			struct gntalloc_gref, next_file);
+		list_del(&gref->next_file);
+		gref->users--;
+		if (gref->users == 0)
+			__del_gref(gref);
+	}
+	kfree(priv);
+	mutex_unlock(&gref_mutex);
+
+	return 0;
+}
+
+static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
+		struct ioctl_gntalloc_alloc_gref __user *arg)
+{
+	int rc = 0;
+	struct ioctl_gntalloc_alloc_gref op;
+	uint32_t *gref_ids;
+
+	pr_debug("%s: priv %p\n", __func__, priv);
+
+	if (copy_from_user(&op, arg, sizeof(op))) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	gref_ids = kcalloc(op.count, sizeof(gref_ids[0]), GFP_TEMPORARY);
+	if (!gref_ids) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	mutex_lock(&gref_mutex);
+	/* Clean up pages that were at zero (local) users but were still mapped
+	 * by remote domains. Since those pages count towards the limit that we
+	 * are about to enforce, removing them here is a good idea.
+	 */
+	do_cleanup();
+	if (gref_size + op.count > limit) {
+		mutex_unlock(&gref_mutex);
+		rc = -ENOSPC;
+		goto out_free;
+	}
+	gref_size += op.count;
+	op.index = priv->index;
+	priv->index += op.count * PAGE_SIZE;
+	mutex_unlock(&gref_mutex);
+
+	rc = add_grefs(&op, gref_ids, priv);
+	if (rc < 0)
+		goto out_free;
+
+	/* Once we finish add_grefs, it is unsafe to touch the new reference,
+	 * since it is possible for a concurrent ioctl to remove it (by guessing
+	 * its index). If the userspace application doesn't provide valid memory
+	 * to write the IDs to, then it will need to close the file in order to
+	 * release - which it will do by segfaulting when it tries to access the
+	 * IDs to close them.
+	 */
+	if (copy_to_user(arg, &op, sizeof(op))) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+	if (copy_to_user(arg->gref_ids, gref_ids,
+			sizeof(gref_ids[0]) * op.count)) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+
+out_free:
+	kfree(gref_ids);
+out:
+	return rc;
+}
+
+static long gntalloc_ioctl_dealloc(struct gntalloc_file_private_data *priv,
+		void __user *arg)
+{
+	int i, rc = 0;
+	struct ioctl_gntalloc_dealloc_gref op;
+	struct gntalloc_gref *gref, *n;
+
+	pr_debug("%s: priv %p\n", __func__, priv);
+
+	if (copy_from_user(&op, arg, sizeof(op))) {
+		rc = -EFAULT;
+		goto dealloc_grant_out;
+	}
+
+	mutex_lock(&gref_mutex);
+	gref = find_grefs(priv, op.index, op.count);
+	if (gref) {
+		/* Remove from the file list only, and decrease reference count.
+		 * The later call to do_cleanup() will remove from gref_list and
+		 * free the memory if the pages aren't mapped anywhere.
+		 */
+		for (i = 0; i < op.count; i++) {
+			n = list_entry(gref->next_file.next,
+				struct gntalloc_gref, next_file);
+			list_del(&gref->next_file);
+			gref->users--;
+			gref = n;
+		}
+	} else {
+		rc = -EINVAL;
+	}
+
+	do_cleanup();
+
+	mutex_unlock(&gref_mutex);
+dealloc_grant_out:
+	return rc;
+}
+
+static long gntalloc_ioctl_unmap_notify(struct gntalloc_file_private_data *priv,
+		void __user *arg)
+{
+	struct ioctl_gntalloc_unmap_notify op;
+	struct gntalloc_gref *gref;
+	uint64_t index;
+	int pgoff;
+	int rc;
+
+	if (copy_from_user(&op, arg, sizeof(op)))
+		return -EFAULT;
+
+	index = op.index & ~(PAGE_SIZE - 1);
+	pgoff = op.index & (PAGE_SIZE - 1);
+
+	mutex_lock(&gref_mutex);
+
+	gref = find_grefs(priv, index, 1);
+	if (!gref) {
+		rc = -ENOENT;
+		goto unlock_out;
+	}
+
+	if (op.action & ~(UNMAP_NOTIFY_CLEAR_BYTE|UNMAP_NOTIFY_SEND_EVENT)) {
+		rc = -EINVAL;
+		goto unlock_out;
+	}
+
+	/* We need to grab a reference to the event channel we are going to use
+	 * to send the notify before releasing the reference we may already have
+	 * (if someone has called this ioctl twice). This is required so that
+	 * it is possible to change the clear_byte part of the notification
+	 * without disturbing the event channel part, which may now be the last
+	 * reference to that event channel.
+	 */
+	if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
+		if (evtchn_get(op.event_channel_port)) {
+			rc = -EINVAL;
+			goto unlock_out;
+		}
+	}
+
+	if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT)
+		evtchn_put(gref->notify.event);
+
+	gref->notify.flags = op.action;
+	gref->notify.pgoff = pgoff;
+	gref->notify.event = op.event_channel_port;
+	rc = 0;
+
+ unlock_out:
+	mutex_unlock(&gref_mutex);
+	return rc;
+}
+
+static long gntalloc_ioctl(struct file *filp, unsigned int cmd,
+		unsigned long arg)
+{
+	struct gntalloc_file_private_data *priv = filp->private_data;
+
+	switch (cmd) {
+	case IOCTL_GNTALLOC_ALLOC_GREF:
+		return gntalloc_ioctl_alloc(priv, (void __user *)arg);
+
+	case IOCTL_GNTALLOC_DEALLOC_GREF:
+		return gntalloc_ioctl_dealloc(priv, (void __user *)arg);
+
+	case IOCTL_GNTALLOC_SET_UNMAP_NOTIFY:
+		return gntalloc_ioctl_unmap_notify(priv, (void __user *)arg);
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return 0;
+}
+
+static void gntalloc_vma_open(struct vm_area_struct *vma)
+{
+	struct gntalloc_vma_private_data *priv = vma->vm_private_data;
+
+	if (!priv)
+		return;
+
+	mutex_lock(&gref_mutex);
+	priv->users++;
+	mutex_unlock(&gref_mutex);
+}
+
+static void gntalloc_vma_close(struct vm_area_struct *vma)
+{
+	struct gntalloc_vma_private_data *priv = vma->vm_private_data;
+	struct gntalloc_gref *gref, *next;
+	int i;
+
+	if (!priv)
+		return;
+
+	mutex_lock(&gref_mutex);
+	priv->users--;
+	if (priv->users == 0) {
+		gref = priv->gref;
+		for (i = 0; i < priv->count; i++) {
+			gref->users--;
+			next = list_entry(gref->next_gref.next,
+					  struct gntalloc_gref, next_gref);
+			if (gref->users == 0)
+				__del_gref(gref);
+			gref = next;
+		}
+		kfree(priv);
+	}
+	mutex_unlock(&gref_mutex);
+}
+
+static struct vm_operations_struct gntalloc_vmops = {
+	.open = gntalloc_vma_open,
+	.close = gntalloc_vma_close,
+};
+
+static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct gntalloc_file_private_data *priv = filp->private_data;
+	struct gntalloc_vma_private_data *vm_priv;
+	struct gntalloc_gref *gref;
+	int count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	int rv, i;
+
+	if (!(vma->vm_flags & VM_SHARED)) {
+		printk(KERN_ERR "%s: Mapping must be shared.\n", __func__);
+		return -EINVAL;
+	}
+
+	vm_priv = kmalloc(sizeof(*vm_priv), GFP_KERNEL);
+	if (!vm_priv)
+		return -ENOMEM;
+
+	mutex_lock(&gref_mutex);
+
+	pr_debug("%s: priv %p,%p, page %lu+%d\n", __func__,
+		       priv, vm_priv, vma->vm_pgoff, count);
+
+	gref = find_grefs(priv, vma->vm_pgoff << PAGE_SHIFT, count);
+	if (gref == NULL) {
+		rv = -ENOENT;
+		pr_debug("%s: Could not find grant reference",
+				__func__);
+		kfree(vm_priv);
+		goto out_unlock;
+	}
+
+	vm_priv->gref = gref;
+	vm_priv->users = 1;
+	vm_priv->count = count;
+
+	vma->vm_private_data = vm_priv;
+
+	vma->vm_flags |= VM_RESERVED | VM_DONTEXPAND;
+
+	vma->vm_ops = &gntalloc_vmops;
+
+	for (i = 0; i < count; i++) {
+		gref->users++;
+		rv = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE,
+				gref->page);
+		if (rv)
+			goto out_unlock;
+
+		gref = list_entry(gref->next_file.next,
+				struct gntalloc_gref, next_file);
+	}
+	rv = 0;
+
+out_unlock:
+	mutex_unlock(&gref_mutex);
+	return rv;
+}
+
+static const struct file_operations gntalloc_fops = {
+	.owner = THIS_MODULE,
+	.open = gntalloc_open,
+	.release = gntalloc_release,
+	.unlocked_ioctl = gntalloc_ioctl,
+	.mmap = gntalloc_mmap
+};
+
+/*
+ * -------------------------------------
+ * Module creation/destruction.
+ * -------------------------------------
+ */
+static struct miscdevice gntalloc_miscdev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "xen/gntalloc",
+	.fops	= &gntalloc_fops,
+};
+
+static int __init gntalloc_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	err = misc_register(&gntalloc_miscdev);
+	if (err != 0) {
+		printk(KERN_ERR "Could not register misc gntalloc device\n");
+		return err;
+	}
+
+	pr_debug("Created grant allocation device at %d,%d\n",
+			MISC_MAJOR, gntalloc_miscdev.minor);
+
+	return 0;
+}
+
+static void __exit gntalloc_exit(void)
+{
+	misc_deregister(&gntalloc_miscdev);
+}
+
+module_init(gntalloc_init);
+module_exit(gntalloc_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Carter Weatherly <carter.weatherly@jhuapl.edu>, "
+		"Daniel De Graaf <dgdegra@tycho.nsa.gov>");
+MODULE_DESCRIPTION("User-space grant reference allocator driver");
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
new file mode 100644
index 00000000..1ffd03bf
--- /dev/null
+++ b/drivers/xen/gntdev.c
@@ -0,0 +1,823 @@
+/******************************************************************************
+ * gntdev.c
+ *
+ * Device for accessing (in user-space) pages that have been granted by other
+ * domains.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#undef DEBUG
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+
+#include <xen/xen.h>
+#include <xen/grant_table.h>
+#include <xen/balloon.h>
+#include <xen/gntdev.h>
+#include <xen/events.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
+	      "Gerd Hoffmann <kraxel@redhat.com>");
+MODULE_DESCRIPTION("User-space granted page access driver");
+
+static int limit = 1024*1024;
+module_param(limit, int, 0644);
+MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by "
+		"the gntdev device");
+
+static atomic_t pages_mapped = ATOMIC_INIT(0);
+
+static int use_ptemod;
+
+struct gntdev_priv {
+	struct list_head maps;
+	/* lock protects maps from concurrent changes */
+	spinlock_t lock;
+	struct mm_struct *mm;
+	struct mmu_notifier mn;
+};
+
+struct unmap_notify {
+	int flags;
+	/* Address relative to the start of the grant_map */
+	int addr;
+	int event;
+};
+
+struct grant_map {
+	struct list_head next;
+	struct vm_area_struct *vma;
+	int index;
+	int count;
+	int flags;
+	atomic_t users;
+	struct unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct page **pages;
+};
+
+static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
+
+/* ------------------------------------------------------------------ */
+
+static void gntdev_print_maps(struct gntdev_priv *priv,
+			      char *text, int text_index)
+{
+#ifdef DEBUG
+	struct grant_map *map;
+
+	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
+	list_for_each_entry(map, &priv->maps, next)
+		pr_debug("  index %2d, count %2d %s\n",
+		       map->index, map->count,
+		       map->index == text_index && text ? text : "");
+#endif
+}
+
+static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
+{
+	struct grant_map *add;
+	int i;
+
+	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
+	if (NULL == add)
+		return NULL;
+
+	add->grants    = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
+	add->map_ops   = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
+	add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
+	add->kmap_ops  = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+	add->pages     = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
+	if (NULL == add->grants    ||
+	    NULL == add->map_ops   ||
+	    NULL == add->unmap_ops ||
+	    NULL == add->kmap_ops  ||
+	    NULL == add->pages)
+		goto err;
+
+	if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
+		goto err;
+
+	for (i = 0; i < count; i++) {
+		add->map_ops[i].handle = -1;
+		add->unmap_ops[i].handle = -1;
+		add->kmap_ops[i].handle = -1;
+	}
+
+	add->index = 0;
+	add->count = count;
+	atomic_set(&add->users, 1);
+
+	return add;
+
+err:
+	kfree(add->pages);
+	kfree(add->grants);
+	kfree(add->map_ops);
+	kfree(add->unmap_ops);
+	kfree(add->kmap_ops);
+	kfree(add);
+	return NULL;
+}
+
+static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
+{
+	struct grant_map *map;
+
+	list_for_each_entry(map, &priv->maps, next) {
+		if (add->index + add->count < map->index) {
+			list_add_tail(&add->next, &map->next);
+			goto done;
+		}
+		add->index = map->index + map->count;
+	}
+	list_add_tail(&add->next, &priv->maps);
+
+done:
+	gntdev_print_maps(priv, "[new]", add->index);
+}
+
+static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
+		int index, int count)
+{
+	struct grant_map *map;
+
+	list_for_each_entry(map, &priv->maps, next) {
+		if (map->index != index)
+			continue;
+		if (count && map->count != count)
+			continue;
+		return map;
+	}
+	return NULL;
+}
+
+static void gntdev_put_map(struct grant_map *map)
+{
+	if (!map)
+		return;
+
+	if (!atomic_dec_and_test(&map->users))
+		return;
+
+	atomic_sub(map->count, &pages_mapped);
+
+	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
+		notify_remote_via_evtchn(map->notify.event);
+		evtchn_put(map->notify.event);
+	}
+
+	if (map->pages) {
+		if (!use_ptemod)
+			unmap_grant_pages(map, 0, map->count);
+
+		free_xenballooned_pages(map->count, map->pages);
+	}
+	kfree(map->pages);
+	kfree(map->grants);
+	kfree(map->map_ops);
+	kfree(map->unmap_ops);
+	kfree(map);
+}
+
+/* ------------------------------------------------------------------ */
+
+static int find_grant_ptes(pte_t *pte, pgtable_t token,
+		unsigned long addr, void *data)
+{
+	struct grant_map *map = data;
+	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
+	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
+	u64 pte_maddr;
+
+	BUG_ON(pgnr >= map->count);
+	pte_maddr = arbitrary_virt_to_machine(pte).maddr;
+
+	gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
+			  map->grants[pgnr].ref,
+			  map->grants[pgnr].domid);
+	gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
+			    -1 /* handle */);
+	return 0;
+}
+
+static int map_grant_pages(struct grant_map *map)
+{
+	int i, err = 0;
+
+	if (!use_ptemod) {
+		/* Note: it could already be mapped */
+		if (map->map_ops[0].handle != -1)
+			return 0;
+		for (i = 0; i < map->count; i++) {
+			unsigned long addr = (unsigned long)
+				pfn_to_kaddr(page_to_pfn(map->pages[i]));
+			gnttab_set_map_op(&map->map_ops[i], addr, map->flags,
+				map->grants[i].ref,
+				map->grants[i].domid);
+			gnttab_set_unmap_op(&map->unmap_ops[i], addr,
+				map->flags, -1 /* handle */);
+		}
+	} else {
+		/*
+		 * Setup the map_ops corresponding to the pte entries pointing
+		 * to the kernel linear addresses of the struct pages.
+		 * These ptes are completely different from the user ptes dealt
+		 * with find_grant_ptes.
+		 */
+		for (i = 0; i < map->count; i++) {
+			unsigned level;
+			unsigned long address = (unsigned long)
+				pfn_to_kaddr(page_to_pfn(map->pages[i]));
+			pte_t *ptep;
+			u64 pte_maddr = 0;
+			BUG_ON(PageHighMem(map->pages[i]));
+
+			ptep = lookup_address(address, &level);
+			pte_maddr = arbitrary_virt_to_machine(ptep).maddr;
+			gnttab_set_map_op(&map->kmap_ops[i], pte_maddr,
+				map->flags |
+				GNTMAP_host_map |
+				GNTMAP_contains_pte,
+				map->grants[i].ref,
+				map->grants[i].domid);
+		}
+	}
+
+	pr_debug("map %d+%d\n", map->index, map->count);
+	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
+			map->pages, map->count);
+	if (err)
+		return err;
+
+	for (i = 0; i < map->count; i++) {
+		if (map->map_ops[i].status)
+			err = -EINVAL;
+		else {
+			BUG_ON(map->map_ops[i].handle == -1);
+			map->unmap_ops[i].handle = map->map_ops[i].handle;
+			pr_debug("map handle=%d\n", map->map_ops[i].handle);
+		}
+	}
+	return err;
+}
+
+static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
+{
+	int i, err = 0;
+
+	if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
+		int pgno = (map->notify.addr >> PAGE_SHIFT);
+		if (pgno >= offset && pgno < offset + pages && use_ptemod) {
+			void __user *tmp = (void __user *)
+				map->vma->vm_start + map->notify.addr;
+			err = copy_to_user(tmp, &err, 1);
+			if (err)
+				return -EFAULT;
+			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
+		} else if (pgno >= offset && pgno < offset + pages) {
+			uint8_t *tmp = kmap(map->pages[pgno]);
+			tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
+			kunmap(map->pages[pgno]);
+			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
+		}
+	}
+
+	err = gnttab_unmap_refs(map->unmap_ops + offset, map->pages + offset,
+				pages, true);
+	if (err)
+		return err;
+
+	for (i = 0; i < pages; i++) {
+		if (map->unmap_ops[offset+i].status)
+			err = -EINVAL;
+		pr_debug("unmap handle=%d st=%d\n",
+			map->unmap_ops[offset+i].handle,
+			map->unmap_ops[offset+i].status);
+		map->unmap_ops[offset+i].handle = -1;
+	}
+	return err;
+}
+
+static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
+{
+	int range, err = 0;
+
+	pr_debug("unmap %d+%d [%d+%d]\n", map->index, map->count, offset, pages);
+
+	/* It is possible the requested range will have a "hole" where we
+	 * already unmapped some of the grants. Only unmap valid ranges.
+	 */
+	while (pages && !err) {
+		while (pages && map->unmap_ops[offset].handle == -1) {
+			offset++;
+			pages--;
+		}
+		range = 0;
+		while (range < pages) {
+			if (map->unmap_ops[offset+range].handle == -1) {
+				range--;
+				break;
+			}
+			range++;
+		}
+		err = __unmap_grant_pages(map, offset, range);
+		offset += range;
+		pages -= range;
+	}
+
+	return err;
+}
+
+/* ------------------------------------------------------------------ */
+
+static void gntdev_vma_open(struct vm_area_struct *vma)
+{
+	struct grant_map *map = vma->vm_private_data;
+
+	pr_debug("gntdev_vma_open %p\n", vma);
+	atomic_inc(&map->users);
+}
+
+static void gntdev_vma_close(struct vm_area_struct *vma)
+{
+	struct grant_map *map = vma->vm_private_data;
+
+	pr_debug("gntdev_vma_close %p\n", vma);
+	map->vma = NULL;
+	vma->vm_private_data = NULL;
+	gntdev_put_map(map);
+}
+
+static struct vm_operations_struct gntdev_vmops = {
+	.open = gntdev_vma_open,
+	.close = gntdev_vma_close,
+};
+
+/* ------------------------------------------------------------------ */
+
+static void mn_invl_range_start(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long start, unsigned long end)
+{
+	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
+	struct grant_map *map;
+	unsigned long mstart, mend;
+	int err;
+
+	spin_lock(&priv->lock);
+	list_for_each_entry(map, &priv->maps, next) {
+		if (!map->vma)
+			continue;
+		if (map->vma->vm_start >= end)
+			continue;
+		if (map->vma->vm_end <= start)
+			continue;
+		mstart = max(start, map->vma->vm_start);
+		mend   = min(end,   map->vma->vm_end);
+		pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
+				map->index, map->count,
+				map->vma->vm_start, map->vma->vm_end,
+				start, end, mstart, mend);
+		err = unmap_grant_pages(map,
+					(mstart - map->vma->vm_start) >> PAGE_SHIFT,
+					(mend - mstart) >> PAGE_SHIFT);
+		WARN_ON(err);
+	}
+	spin_unlock(&priv->lock);
+}
+
+static void mn_invl_page(struct mmu_notifier *mn,
+			 struct mm_struct *mm,
+			 unsigned long address)
+{
+	mn_invl_range_start(mn, mm, address, address + PAGE_SIZE);
+}
+
+static void mn_release(struct mmu_notifier *mn,
+		       struct mm_struct *mm)
+{
+	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
+	struct grant_map *map;
+	int err;
+
+	spin_lock(&priv->lock);
+	list_for_each_entry(map, &priv->maps, next) {
+		if (!map->vma)
+			continue;
+		pr_debug("map %d+%d (%lx %lx)\n",
+				map->index, map->count,
+				map->vma->vm_start, map->vma->vm_end);
+		err = unmap_grant_pages(map, /* offset */ 0, map->count);
+		WARN_ON(err);
+	}
+	spin_unlock(&priv->lock);
+}
+
+struct mmu_notifier_ops gntdev_mmu_ops = {
+	.release                = mn_release,
+	.invalidate_page        = mn_invl_page,
+	.invalidate_range_start = mn_invl_range_start,
+};
+
+/* ------------------------------------------------------------------ */
+
+static int gntdev_open(struct inode *inode, struct file *flip)
+{
+	struct gntdev_priv *priv;
+	int ret = 0;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&priv->maps);
+	spin_lock_init(&priv->lock);
+
+	if (use_ptemod) {
+		priv->mm = get_task_mm(current);
+		if (!priv->mm) {
+			kfree(priv);
+			return -ENOMEM;
+		}
+		priv->mn.ops = &gntdev_mmu_ops;
+		ret = mmu_notifier_register(&priv->mn, priv->mm);
+		mmput(priv->mm);
+	}
+
+	if (ret) {
+		kfree(priv);
+		return ret;
+	}
+
+	flip->private_data = priv;
+	pr_debug("priv %p\n", priv);
+
+	return 0;
+}
+
+static int gntdev_release(struct inode *inode, struct file *flip)
+{
+	struct gntdev_priv *priv = flip->private_data;
+	struct grant_map *map;
+
+	pr_debug("priv %p\n", priv);
+
+	while (!list_empty(&priv->maps)) {
+		map = list_entry(priv->maps.next, struct grant_map, next);
+		list_del(&map->next);
+		gntdev_put_map(map);
+	}
+
+	if (use_ptemod)
+		mmu_notifier_unregister(&priv->mn, priv->mm);
+	kfree(priv);
+	return 0;
+}
+
+static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
+				       struct ioctl_gntdev_map_grant_ref __user *u)
+{
+	struct ioctl_gntdev_map_grant_ref op;
+	struct grant_map *map;
+	int err;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+	pr_debug("priv %p, add %d\n", priv, op.count);
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	err = -ENOMEM;
+	map = gntdev_alloc_map(priv, op.count);
+	if (!map)
+		return err;
+
+	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
+		pr_debug("can't map: over limit\n");
+		gntdev_put_map(map);
+		return err;
+	}
+
+	if (copy_from_user(map->grants, &u->refs,
+			   sizeof(map->grants[0]) * op.count) != 0) {
+		gntdev_put_map(map);
+		return err;
+	}
+
+	spin_lock(&priv->lock);
+	gntdev_add_map(priv, map);
+	op.index = map->index << PAGE_SHIFT;
+	spin_unlock(&priv->lock);
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return 0;
+}
+
+static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
+					 struct ioctl_gntdev_unmap_grant_ref __user *u)
+{
+	struct ioctl_gntdev_unmap_grant_ref op;
+	struct grant_map *map;
+	int err = -ENOENT;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+	pr_debug("priv %p, del %d+%d\n", priv, (int)op.index, (int)op.count);
+
+	spin_lock(&priv->lock);
+	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
+	if (map) {
+		list_del(&map->next);
+		err = 0;
+	}
+	spin_unlock(&priv->lock);
+	if (map)
+		gntdev_put_map(map);
+	return err;
+}
+
+static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
+					      struct ioctl_gntdev_get_offset_for_vaddr __user *u)
+{
+	struct ioctl_gntdev_get_offset_for_vaddr op;
+	struct vm_area_struct *vma;
+	struct grant_map *map;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+	pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr);
+
+	vma = find_vma(current->mm, op.vaddr);
+	if (!vma || vma->vm_ops != &gntdev_vmops)
+		return -EINVAL;
+
+	map = vma->vm_private_data;
+	if (!map)
+		return -EINVAL;
+
+	op.offset = map->index << PAGE_SHIFT;
+	op.count = map->count;
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		return -EFAULT;
+	return 0;
+}
+
+static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
+{
+	struct ioctl_gntdev_unmap_notify op;
+	struct grant_map *map;
+	int rc;
+	int out_flags;
+	unsigned int out_event;
+
+	if (copy_from_user(&op, u, sizeof(op)))
+		return -EFAULT;
+
+	if (op.action & ~(UNMAP_NOTIFY_CLEAR_BYTE|UNMAP_NOTIFY_SEND_EVENT))
+		return -EINVAL;
+
+	/* We need to grab a reference to the event channel we are going to use
+	 * to send the notify before releasing the reference we may already have
+	 * (if someone has called this ioctl twice). This is required so that
+	 * it is possible to change the clear_byte part of the notification
+	 * without disturbing the event channel part, which may now be the last
+	 * reference to that event channel.
+	 */
+	if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
+		if (evtchn_get(op.event_channel_port))
+			return -EINVAL;
+	}
+
+	out_flags = op.action;
+	out_event = op.event_channel_port;
+
+	spin_lock(&priv->lock);
+
+	list_for_each_entry(map, &priv->maps, next) {
+		uint64_t begin = map->index << PAGE_SHIFT;
+		uint64_t end = (map->index + map->count) << PAGE_SHIFT;
+		if (op.index >= begin && op.index < end)
+			goto found;
+	}
+	rc = -ENOENT;
+	goto unlock_out;
+
+ found:
+	if ((op.action & UNMAP_NOTIFY_CLEAR_BYTE) &&
+			(map->flags & GNTMAP_readonly)) {
+		rc = -EINVAL;
+		goto unlock_out;
+	}
+
+	out_flags = map->notify.flags;
+	out_event = map->notify.event;
+
+	map->notify.flags = op.action;
+	map->notify.addr = op.index - (map->index << PAGE_SHIFT);
+	map->notify.event = op.event_channel_port;
+
+	rc = 0;
+
+ unlock_out:
+	spin_unlock(&priv->lock);
+
+	/* Drop the reference to the event channel we did not save in the map */
+	if (out_flags & UNMAP_NOTIFY_SEND_EVENT)
+		evtchn_put(out_event);
+
+	return rc;
+}
+
+static long gntdev_ioctl(struct file *flip,
+			 unsigned int cmd, unsigned long arg)
+{
+	struct gntdev_priv *priv = flip->private_data;
+	void __user *ptr = (void __user *)arg;
+
+	switch (cmd) {
+	case IOCTL_GNTDEV_MAP_GRANT_REF:
+		return gntdev_ioctl_map_grant_ref(priv, ptr);
+
+	case IOCTL_GNTDEV_UNMAP_GRANT_REF:
+		return gntdev_ioctl_unmap_grant_ref(priv, ptr);
+
+	case IOCTL_GNTDEV_GET_OFFSET_FOR_VADDR:
+		return gntdev_ioctl_get_offset_for_vaddr(priv, ptr);
+
+	case IOCTL_GNTDEV_SET_UNMAP_NOTIFY:
+		return gntdev_ioctl_notify(priv, ptr);
+
+	default:
+		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
+		return -ENOIOCTLCMD;
+	}
+
+	return 0;
+}
+
+static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
+{
+	struct gntdev_priv *priv = flip->private_data;
+	int index = vma->vm_pgoff;
+	int count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	struct grant_map *map;
+	int i, err = -EINVAL;
+
+	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	pr_debug("map %d+%d at %lx (pgoff %lx)\n",
+			index, count, vma->vm_start, vma->vm_pgoff);
+
+	spin_lock(&priv->lock);
+	map = gntdev_find_map_index(priv, index, count);
+	if (!map)
+		goto unlock_out;
+	if (use_ptemod && map->vma)
+		goto unlock_out;
+	if (use_ptemod && priv->mm != vma->vm_mm) {
+		printk(KERN_WARNING "Huh? Other mm?\n");
+		goto unlock_out;
+	}
+
+	atomic_inc(&map->users);
+
+	vma->vm_ops = &gntdev_vmops;
+
+	vma->vm_flags |= VM_RESERVED|VM_DONTEXPAND;
+
+	if (use_ptemod)
+		vma->vm_flags |= VM_DONTCOPY;
+
+	vma->vm_private_data = map;
+
+	if (use_ptemod)
+		map->vma = vma;
+
+	if (map->flags) {
+		if ((vma->vm_flags & VM_WRITE) &&
+				(map->flags & GNTMAP_readonly))
+			goto out_unlock_put;
+	} else {
+		map->flags = GNTMAP_host_map;
+		if (!(vma->vm_flags & VM_WRITE))
+			map->flags |= GNTMAP_readonly;
+	}
+
+	spin_unlock(&priv->lock);
+
+	if (use_ptemod) {
+		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
+					  vma->vm_end - vma->vm_start,
+					  find_grant_ptes, map);
+		if (err) {
+			printk(KERN_WARNING "find_grant_ptes() failure.\n");
+			goto out_put_map;
+		}
+	}
+
+	err = map_grant_pages(map);
+	if (err)
+		goto out_put_map;
+
+	if (!use_ptemod) {
+		for (i = 0; i < count; i++) {
+			err = vm_insert_page(vma, vma->vm_start + i*PAGE_SIZE,
+				map->pages[i]);
+			if (err)
+				goto out_put_map;
+		}
+	}
+
+	return 0;
+
+unlock_out:
+	spin_unlock(&priv->lock);
+	return err;
+
+out_unlock_put:
+	spin_unlock(&priv->lock);
+out_put_map:
+	if (use_ptemod)
+		map->vma = NULL;
+	gntdev_put_map(map);
+	return err;
+}
+
+static const struct file_operations gntdev_fops = {
+	.owner = THIS_MODULE,
+	.open = gntdev_open,
+	.release = gntdev_release,
+	.mmap = gntdev_mmap,
+	.unlocked_ioctl = gntdev_ioctl
+};
+
+static struct miscdevice gntdev_miscdev = {
+	.minor        = MISC_DYNAMIC_MINOR,
+	.name         = "xen/gntdev",
+	.fops         = &gntdev_fops,
+};
+
+/* ------------------------------------------------------------------ */
+
+static int __init gntdev_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	use_ptemod = xen_pv_domain();
+
+	err = misc_register(&gntdev_miscdev);
+	if (err != 0) {
+		printk(KERN_ERR "Could not register gntdev device\n");
+		return err;
+	}
+	return 0;
+}
+
+static void __exit gntdev_exit(void)
+{
+	misc_deregister(&gntdev_miscdev);
+}
+
+module_init(gntdev_init);
+module_exit(gntdev_exit);
+
+/* ------------------------------------------------------------------ */
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
new file mode 100644
index 00000000..f100ce20
--- /dev/null
+++ b/drivers/xen/grant-table.c
@@ -0,0 +1,1094 @@
+/******************************************************************************
+ * grant_table.c
+ *
+ * Granting foreign access to our memory reservation.
+ *
+ * Copyright (c) 2005-2006, Christopher Clark
+ * Copyright (c) 2004-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+
+#include <xen/xen.h>
+#include <xen/interface/xen.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+#include <xen/interface/memory.h>
+#include <xen/hvc-console.h>
+#include <asm/xen/hypercall.h>
+
+#include <asm/pgtable.h>
+#include <asm/sync_bitops.h>
+
+/* External tools reserve first few grant table entries. */
+#define NR_RESERVED_ENTRIES 8
+#define GNTTAB_LIST_END 0xffffffff
+#define GREFS_PER_GRANT_FRAME \
+(grant_table_version == 1 ?                      \
+(PAGE_SIZE / sizeof(struct grant_entry_v1)) :   \
+(PAGE_SIZE / sizeof(union grant_entry_v2)))
+
+static grant_ref_t **gnttab_list;
+static unsigned int nr_grant_frames;
+static unsigned int boot_max_nr_grant_frames;
+static int gnttab_free_count;
+static grant_ref_t gnttab_free_head;
+static DEFINE_SPINLOCK(gnttab_list_lock);
+unsigned long xen_hvm_resume_frames;
+EXPORT_SYMBOL_GPL(xen_hvm_resume_frames);
+
+static union {
+	struct grant_entry_v1 *v1;
+	union grant_entry_v2 *v2;
+	void *addr;
+} gnttab_shared;
+
+/*This is a structure of function pointers for grant table*/
+struct gnttab_ops {
+	/*
+	 * Mapping a list of frames for storing grant entries. Frames parameter
+	 * is used to store grant table address when grant table being setup,
+	 * nr_gframes is the number of frames to map grant table. Returning
+	 * GNTST_okay means success and negative value means failure.
+	 */
+	int (*map_frames)(unsigned long *frames, unsigned int nr_gframes);
+	/*
+	 * Release a list of frames which are mapped in map_frames for grant
+	 * entry status.
+	 */
+	void (*unmap_frames)(void);
+	/*
+	 * Introducing a valid entry into the grant table, granting the frame of
+	 * this grant entry to domain for accessing or transfering. Ref
+	 * parameter is reference of this introduced grant entry, domid is id of
+	 * granted domain, frame is the page frame to be granted, and flags is
+	 * status of the grant entry to be updated.
+	 */
+	void (*update_entry)(grant_ref_t ref, domid_t domid,
+			     unsigned long frame, unsigned flags);
+	/*
+	 * Stop granting a grant entry to domain for accessing. Ref parameter is
+	 * reference of a grant entry whose grant access will be stopped,
+	 * readonly is not in use in this function. If the grant entry is
+	 * currently mapped for reading or writing, just return failure(==0)
+	 * directly and don't tear down the grant access. Otherwise, stop grant
+	 * access for this entry and return success(==1).
+	 */
+	int (*end_foreign_access_ref)(grant_ref_t ref, int readonly);
+	/*
+	 * Stop granting a grant entry to domain for transfer. Ref parameter is
+	 * reference of a grant entry whose grant transfer will be stopped. If
+	 * tranfer has not started, just reclaim the grant entry and return
+	 * failure(==0). Otherwise, wait for the transfer to complete and then
+	 * return the frame.
+	 */
+	unsigned long (*end_foreign_transfer_ref)(grant_ref_t ref);
+	/*
+	 * Query the status of a grant entry. Ref parameter is reference of
+	 * queried grant entry, return value is the status of queried entry.
+	 * Detailed status(writing/reading) can be gotten from the return value
+	 * by bit operations.
+	 */
+	int (*query_foreign_access)(grant_ref_t ref);
+	/*
+	 * Grant a domain to access a range of bytes within the page referred by
+	 * an available grant entry. Ref parameter is reference of a grant entry
+	 * which will be sub-page accessed, domid is id of grantee domain, frame
+	 * is frame address of subpage grant, flags is grant type and flag
+	 * information, page_off is offset of the range of bytes, and length is
+	 * length of bytes to be accessed.
+	 */
+	void (*update_subpage_entry)(grant_ref_t ref, domid_t domid,
+				     unsigned long frame, int flags,
+				     unsigned page_off, unsigned length);
+	/*
+	 * Redirect an available grant entry on domain A to another grant
+	 * reference of domain B, then allow domain C to use grant reference
+	 * of domain B transitively. Ref parameter is an available grant entry
+	 * reference on domain A, domid is id of domain C which accesses grant
+	 * entry transitively, flags is grant type and flag information,
+	 * trans_domid is id of domain B whose grant entry is finally accessed
+	 * transitively, trans_gref is grant entry transitive reference of
+	 * domain B.
+	 */
+	void (*update_trans_entry)(grant_ref_t ref, domid_t domid, int flags,
+				   domid_t trans_domid, grant_ref_t trans_gref);
+};
+
+static struct gnttab_ops *gnttab_interface;
+
+/*This reflects status of grant entries, so act as a global value*/
+static grant_status_t *grstatus;
+
+static int grant_table_version;
+
+static struct gnttab_free_callback *gnttab_free_callback_list;
+
+static int gnttab_expand(unsigned int req_entries);
+
+#define RPP (PAGE_SIZE / sizeof(grant_ref_t))
+#define SPP (PAGE_SIZE / sizeof(grant_status_t))
+
+static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
+{
+	return &gnttab_list[(entry) / RPP][(entry) % RPP];
+}
+/* This can be used as an l-value */
+#define gnttab_entry(entry) (*__gnttab_entry(entry))
+
+static int get_free_entries(unsigned count)
+{
+	unsigned long flags;
+	int ref, rc = 0;
+	grant_ref_t head;
+
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+
+	if ((gnttab_free_count < count) &&
+	    ((rc = gnttab_expand(count - gnttab_free_count)) < 0)) {
+		spin_unlock_irqrestore(&gnttab_list_lock, flags);
+		return rc;
+	}
+
+	ref = head = gnttab_free_head;
+	gnttab_free_count -= count;
+	while (count-- > 1)
+		head = gnttab_entry(head);
+	gnttab_free_head = gnttab_entry(head);
+	gnttab_entry(head) = GNTTAB_LIST_END;
+
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+
+	return ref;
+}
+
+static void do_free_callbacks(void)
+{
+	struct gnttab_free_callback *callback, *next;
+
+	callback = gnttab_free_callback_list;
+	gnttab_free_callback_list = NULL;
+
+	while (callback != NULL) {
+		next = callback->next;
+		if (gnttab_free_count >= callback->count) {
+			callback->next = NULL;
+			callback->fn(callback->arg);
+		} else {
+			callback->next = gnttab_free_callback_list;
+			gnttab_free_callback_list = callback;
+		}
+		callback = next;
+	}
+}
+
+static inline void check_free_callbacks(void)
+{
+	if (unlikely(gnttab_free_callback_list))
+		do_free_callbacks();
+}
+
+static void put_free_entry(grant_ref_t ref)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+	gnttab_entry(ref) = gnttab_free_head;
+	gnttab_free_head = ref;
+	gnttab_free_count++;
+	check_free_callbacks();
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+
+/*
+ * Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
+ * Introducing a valid entry into the grant table:
+ *  1. Write ent->domid.
+ *  2. Write ent->frame:
+ *      GTF_permit_access:   Frame to which access is permitted.
+ *      GTF_accept_transfer: Pseudo-phys frame slot being filled by new
+ *                           frame, or zero if none.
+ *  3. Write memory barrier (WMB).
+ *  4. Write ent->flags, inc. valid type.
+ */
+static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid,
+				   unsigned long frame, unsigned flags)
+{
+	gnttab_shared.v1[ref].domid = domid;
+	gnttab_shared.v1[ref].frame = frame;
+	wmb();
+	gnttab_shared.v1[ref].flags = flags;
+}
+
+static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid,
+				   unsigned long frame, unsigned flags)
+{
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	gnttab_shared.v2[ref].full_page.frame = frame;
+	wmb();
+	gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags;
+}
+
+/*
+ * Public grant-issuing interface functions
+ */
+void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
+				     unsigned long frame, int readonly)
+{
+	gnttab_interface->update_entry(ref, domid, frame,
+			   GTF_permit_access | (readonly ? GTF_readonly : 0));
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_ref);
+
+int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
+				int readonly)
+{
+	int ref;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+
+	gnttab_grant_foreign_access_ref(ref, domid, frame, readonly);
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
+
+void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
+				    unsigned long frame, int flags,
+				    unsigned page_off,
+				    unsigned length)
+{
+	gnttab_shared.v2[ref].sub_page.frame = frame;
+	gnttab_shared.v2[ref].sub_page.page_off = page_off;
+	gnttab_shared.v2[ref].sub_page.length = length;
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	wmb();
+	gnttab_shared.v2[ref].hdr.flags =
+				GTF_permit_access | GTF_sub_page | flags;
+}
+
+int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid,
+					    unsigned long frame, int flags,
+					    unsigned page_off,
+					    unsigned length)
+{
+	if (flags & (GTF_accept_transfer | GTF_reading |
+		     GTF_writing | GTF_transitive))
+		return -EPERM;
+
+	if (gnttab_interface->update_subpage_entry == NULL)
+		return -ENOSYS;
+
+	gnttab_interface->update_subpage_entry(ref, domid, frame, flags,
+					       page_off, length);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage_ref);
+
+int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame,
+					int flags, unsigned page_off,
+					unsigned length)
+{
+	int ref, rc;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+
+	rc = gnttab_grant_foreign_access_subpage_ref(ref, domid, frame, flags,
+						     page_off, length);
+	if (rc < 0) {
+		put_free_entry(ref);
+		return rc;
+	}
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage);
+
+bool gnttab_subpage_grants_available(void)
+{
+	return gnttab_interface->update_subpage_entry != NULL;
+}
+EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available);
+
+void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
+				  int flags, domid_t trans_domid,
+				  grant_ref_t trans_gref)
+{
+	gnttab_shared.v2[ref].transitive.trans_domid = trans_domid;
+	gnttab_shared.v2[ref].transitive.gref = trans_gref;
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	wmb();
+	gnttab_shared.v2[ref].hdr.flags =
+				GTF_permit_access | GTF_transitive | flags;
+}
+
+int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid,
+					  int flags, domid_t trans_domid,
+					  grant_ref_t trans_gref)
+{
+	if (flags & (GTF_accept_transfer | GTF_reading |
+		     GTF_writing | GTF_sub_page))
+		return -EPERM;
+
+	if (gnttab_interface->update_trans_entry == NULL)
+		return -ENOSYS;
+
+	gnttab_interface->update_trans_entry(ref, domid, flags, trans_domid,
+					     trans_gref);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans_ref);
+
+int gnttab_grant_foreign_access_trans(domid_t domid, int flags,
+				      domid_t trans_domid,
+				      grant_ref_t trans_gref)
+{
+	int ref, rc;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+
+	rc = gnttab_grant_foreign_access_trans_ref(ref, domid, flags,
+						   trans_domid, trans_gref);
+	if (rc < 0) {
+		put_free_entry(ref);
+		return rc;
+	}
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans);
+
+bool gnttab_trans_grants_available(void)
+{
+	return gnttab_interface->update_trans_entry != NULL;
+}
+EXPORT_SYMBOL_GPL(gnttab_trans_grants_available);
+
+static int gnttab_query_foreign_access_v1(grant_ref_t ref)
+{
+	return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing);
+}
+
+static int gnttab_query_foreign_access_v2(grant_ref_t ref)
+{
+	return grstatus[ref] & (GTF_reading|GTF_writing);
+}
+
+int gnttab_query_foreign_access(grant_ref_t ref)
+{
+	return gnttab_interface->query_foreign_access(ref);
+}
+EXPORT_SYMBOL_GPL(gnttab_query_foreign_access);
+
+static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
+{
+	u16 flags, nflags;
+	u16 *pflags;
+
+	pflags = &gnttab_shared.v1[ref].flags;
+	nflags = *pflags;
+	do {
+		flags = nflags;
+		if (flags & (GTF_reading|GTF_writing)) {
+			printk(KERN_ALERT "WARNING: g.e. still in use!\n");
+			return 0;
+		}
+	} while ((nflags = sync_cmpxchg(pflags, flags, 0)) != flags);
+
+	return 1;
+}
+
+static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
+{
+	gnttab_shared.v2[ref].hdr.flags = 0;
+	mb();
+	if (grstatus[ref] & (GTF_reading|GTF_writing)) {
+		return 0;
+	} else {
+		/* The read of grstatus needs to have acquire
+		semantics.  On x86, reads already have
+		that, and we just need to protect against
+		compiler reorderings.  On other
+		architectures we may need a full
+		barrier. */
+#ifdef CONFIG_X86
+		barrier();
+#else
+		mb();
+#endif
+	}
+
+	return 1;
+}
+
+int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+{
+	return gnttab_interface->end_foreign_access_ref(ref, readonly);
+}
+EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
+
+void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
+			       unsigned long page)
+{
+	if (gnttab_end_foreign_access_ref(ref, readonly)) {
+		put_free_entry(ref);
+		if (page != 0)
+			free_page(page);
+	} else {
+		/* XXX This needs to be fixed so that the ref and page are
+		   placed on a list to be freed up later. */
+		printk(KERN_WARNING
+		       "WARNING: leaking g.e. and page still in use!\n");
+	}
+}
+EXPORT_SYMBOL_GPL(gnttab_end_foreign_access);
+
+int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn)
+{
+	int ref;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+	gnttab_grant_foreign_transfer_ref(ref, domid, pfn);
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_transfer);
+
+void gnttab_grant_foreign_transfer_ref(grant_ref_t ref, domid_t domid,
+				       unsigned long pfn)
+{
+	gnttab_interface->update_entry(ref, domid, pfn, GTF_accept_transfer);
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_transfer_ref);
+
+static unsigned long gnttab_end_foreign_transfer_ref_v1(grant_ref_t ref)
+{
+	unsigned long frame;
+	u16           flags;
+	u16          *pflags;
+
+	pflags = &gnttab_shared.v1[ref].flags;
+
+	/*
+	 * If a transfer is not even yet started, try to reclaim the grant
+	 * reference and return failure (== 0).
+	 */
+	while (!((flags = *pflags) & GTF_transfer_committed)) {
+		if (sync_cmpxchg(pflags, flags, 0) == flags)
+			return 0;
+		cpu_relax();
+	}
+
+	/* If a transfer is in progress then wait until it is completed. */
+	while (!(flags & GTF_transfer_completed)) {
+		flags = *pflags;
+		cpu_relax();
+	}
+
+	rmb();	/* Read the frame number /after/ reading completion status. */
+	frame = gnttab_shared.v1[ref].frame;
+	BUG_ON(frame == 0);
+
+	return frame;
+}
+
+static unsigned long gnttab_end_foreign_transfer_ref_v2(grant_ref_t ref)
+{
+	unsigned long frame;
+	u16           flags;
+	u16          *pflags;
+
+	pflags = &gnttab_shared.v2[ref].hdr.flags;
+
+	/*
+	 * If a transfer is not even yet started, try to reclaim the grant
+	 * reference and return failure (== 0).
+	 */
+	while (!((flags = *pflags) & GTF_transfer_committed)) {
+		if (sync_cmpxchg(pflags, flags, 0) == flags)
+			return 0;
+		cpu_relax();
+	}
+
+	/* If a transfer is in progress then wait until it is completed. */
+	while (!(flags & GTF_transfer_completed)) {
+		flags = *pflags;
+		cpu_relax();
+	}
+
+	rmb();  /* Read the frame number /after/ reading completion status. */
+	frame = gnttab_shared.v2[ref].full_page.frame;
+	BUG_ON(frame == 0);
+
+	return frame;
+}
+
+unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref)
+{
+	return gnttab_interface->end_foreign_transfer_ref(ref);
+}
+EXPORT_SYMBOL_GPL(gnttab_end_foreign_transfer_ref);
+
+unsigned long gnttab_end_foreign_transfer(grant_ref_t ref)
+{
+	unsigned long frame = gnttab_end_foreign_transfer_ref(ref);
+	put_free_entry(ref);
+	return frame;
+}
+EXPORT_SYMBOL_GPL(gnttab_end_foreign_transfer);
+
+void gnttab_free_grant_reference(grant_ref_t ref)
+{
+	put_free_entry(ref);
+}
+EXPORT_SYMBOL_GPL(gnttab_free_grant_reference);
+
+void gnttab_free_grant_references(grant_ref_t head)
+{
+	grant_ref_t ref;
+	unsigned long flags;
+	int count = 1;
+	if (head == GNTTAB_LIST_END)
+		return;
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+	ref = head;
+	while (gnttab_entry(ref) != GNTTAB_LIST_END) {
+		ref = gnttab_entry(ref);
+		count++;
+	}
+	gnttab_entry(ref) = gnttab_free_head;
+	gnttab_free_head = head;
+	gnttab_free_count += count;
+	check_free_callbacks();
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_free_grant_references);
+
+int gnttab_alloc_grant_references(u16 count, grant_ref_t *head)
+{
+	int h = get_free_entries(count);
+
+	if (h < 0)
+		return -ENOSPC;
+
+	*head = h;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_grant_references);
+
+int gnttab_empty_grant_references(const grant_ref_t *private_head)
+{
+	return (*private_head == GNTTAB_LIST_END);
+}
+EXPORT_SYMBOL_GPL(gnttab_empty_grant_references);
+
+int gnttab_claim_grant_reference(grant_ref_t *private_head)
+{
+	grant_ref_t g = *private_head;
+	if (unlikely(g == GNTTAB_LIST_END))
+		return -ENOSPC;
+	*private_head = gnttab_entry(g);
+	return g;
+}
+EXPORT_SYMBOL_GPL(gnttab_claim_grant_reference);
+
+void gnttab_release_grant_reference(grant_ref_t *private_head,
+				    grant_ref_t release)
+{
+	gnttab_entry(release) = *private_head;
+	*private_head = release;
+}
+EXPORT_SYMBOL_GPL(gnttab_release_grant_reference);
+
+void gnttab_request_free_callback(struct gnttab_free_callback *callback,
+				  void (*fn)(void *), void *arg, u16 count)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+	if (callback->next)
+		goto out;
+	callback->fn = fn;
+	callback->arg = arg;
+	callback->count = count;
+	callback->next = gnttab_free_callback_list;
+	gnttab_free_callback_list = callback;
+	check_free_callbacks();
+out:
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_request_free_callback);
+
+void gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
+{
+	struct gnttab_free_callback **pcb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+	for (pcb = &gnttab_free_callback_list; *pcb; pcb = &(*pcb)->next) {
+		if (*pcb == callback) {
+			*pcb = callback->next;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_cancel_free_callback);
+
+static int grow_gnttab_list(unsigned int more_frames)
+{
+	unsigned int new_nr_grant_frames, extra_entries, i;
+	unsigned int nr_glist_frames, new_nr_glist_frames;
+
+	new_nr_grant_frames = nr_grant_frames + more_frames;
+	extra_entries       = more_frames * GREFS_PER_GRANT_FRAME;
+
+	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+	new_nr_glist_frames =
+		(new_nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+	for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
+		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
+		if (!gnttab_list[i])
+			goto grow_nomem;
+	}
+
+
+	for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames;
+	     i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++)
+		gnttab_entry(i) = i + 1;
+
+	gnttab_entry(i) = gnttab_free_head;
+	gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames;
+	gnttab_free_count += extra_entries;
+
+	nr_grant_frames = new_nr_grant_frames;
+
+	check_free_callbacks();
+
+	return 0;
+
+grow_nomem:
+	for ( ; i >= nr_glist_frames; i--)
+		free_page((unsigned long) gnttab_list[i]);
+	return -ENOMEM;
+}
+
+static unsigned int __max_nr_grant_frames(void)
+{
+	struct gnttab_query_size query;
+	int rc;
+
+	query.dom = DOMID_SELF;
+
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_query_size, &query, 1);
+	if ((rc < 0) || (query.status != GNTST_okay))
+		return 4; /* Legacy max supported number of frames */
+
+	return query.max_nr_frames;
+}
+
+unsigned int gnttab_max_grant_frames(void)
+{
+	unsigned int xen_max = __max_nr_grant_frames();
+
+	if (xen_max > boot_max_nr_grant_frames)
+		return boot_max_nr_grant_frames;
+	return xen_max;
+}
+EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
+
+int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
+		    struct gnttab_map_grant_ref *kmap_ops,
+		    struct page **pages, unsigned int count)
+{
+	int i, ret;
+	pte_t *pte;
+	unsigned long mfn;
+
+	ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
+	if (ret)
+		return ret;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		/* Do not add to override if the map failed. */
+		if (map_ops[i].status)
+			continue;
+
+		if (map_ops[i].flags & GNTMAP_contains_pte) {
+			pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
+				(map_ops[i].host_addr & ~PAGE_MASK));
+			mfn = pte_mfn(*pte);
+		} else {
+			mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
+		}
+		ret = m2p_add_override(mfn, pages[i], kmap_ops ?
+				       &kmap_ops[i] : NULL);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_map_refs);
+
+int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
+		      struct page **pages, unsigned int count, bool clear_pte)
+{
+	int i, ret;
+
+	ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
+	if (ret)
+		return ret;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		ret = m2p_remove_override(pages[i], clear_pte);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
+
+static unsigned nr_status_frames(unsigned nr_grant_frames)
+{
+	return (nr_grant_frames * GREFS_PER_GRANT_FRAME + SPP - 1) / SPP;
+}
+
+static int gnttab_map_frames_v1(unsigned long *frames, unsigned int nr_gframes)
+{
+	int rc;
+
+	rc = arch_gnttab_map_shared(frames, nr_gframes,
+				    gnttab_max_grant_frames(),
+				    &gnttab_shared.addr);
+	BUG_ON(rc);
+
+	return 0;
+}
+
+static void gnttab_unmap_frames_v1(void)
+{
+	arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
+}
+
+static int gnttab_map_frames_v2(unsigned long *frames, unsigned int nr_gframes)
+{
+	uint64_t *sframes;
+	unsigned int nr_sframes;
+	struct gnttab_get_status_frames getframes;
+	int rc;
+
+	nr_sframes = nr_status_frames(nr_gframes);
+
+	/* No need for kzalloc as it is initialized in following hypercall
+	 * GNTTABOP_get_status_frames.
+	 */
+	sframes = kmalloc(nr_sframes  * sizeof(uint64_t), GFP_ATOMIC);
+	if (!sframes)
+		return -ENOMEM;
+
+	getframes.dom        = DOMID_SELF;
+	getframes.nr_frames  = nr_sframes;
+	set_xen_guest_handle(getframes.frame_list, sframes);
+
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames,
+				       &getframes, 1);
+	if (rc == -ENOSYS) {
+		kfree(sframes);
+		return -ENOSYS;
+	}
+
+	BUG_ON(rc || getframes.status);
+
+	rc = arch_gnttab_map_status(sframes, nr_sframes,
+				    nr_status_frames(gnttab_max_grant_frames()),
+				    &grstatus);
+	BUG_ON(rc);
+	kfree(sframes);
+
+	rc = arch_gnttab_map_shared(frames, nr_gframes,
+				    gnttab_max_grant_frames(),
+				    &gnttab_shared.addr);
+	BUG_ON(rc);
+
+	return 0;
+}
+
+static void gnttab_unmap_frames_v2(void)
+{
+	arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
+	arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames));
+}
+
+static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
+{
+	struct gnttab_setup_table setup;
+	unsigned long *frames;
+	unsigned int nr_gframes = end_idx + 1;
+	int rc;
+
+	if (xen_hvm_domain()) {
+		struct xen_add_to_physmap xatp;
+		unsigned int i = end_idx;
+		rc = 0;
+		/*
+		 * Loop backwards, so that the first hypercall has the largest
+		 * index, ensuring that the table will grow only once.
+		 */
+		do {
+			xatp.domid = DOMID_SELF;
+			xatp.idx = i;
+			xatp.space = XENMAPSPACE_grant_table;
+			xatp.gpfn = (xen_hvm_resume_frames >> PAGE_SHIFT) + i;
+			rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp);
+			if (rc != 0) {
+				printk(KERN_WARNING
+						"grant table add_to_physmap failed, err=%d\n", rc);
+				break;
+			}
+		} while (i-- > start_idx);
+
+		return rc;
+	}
+
+	/* No need for kzalloc as it is initialized in following hypercall
+	 * GNTTABOP_setup_table.
+	 */
+	frames = kmalloc(nr_gframes * sizeof(unsigned long), GFP_ATOMIC);
+	if (!frames)
+		return -ENOMEM;
+
+	setup.dom        = DOMID_SELF;
+	setup.nr_frames  = nr_gframes;
+	set_xen_guest_handle(setup.frame_list, frames);
+
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1);
+	if (rc == -ENOSYS) {
+		kfree(frames);
+		return -ENOSYS;
+	}
+
+	BUG_ON(rc || setup.status);
+
+	rc = gnttab_interface->map_frames(frames, nr_gframes);
+
+	kfree(frames);
+
+	return rc;
+}
+
+static struct gnttab_ops gnttab_v1_ops = {
+	.map_frames			= gnttab_map_frames_v1,
+	.unmap_frames			= gnttab_unmap_frames_v1,
+	.update_entry			= gnttab_update_entry_v1,
+	.end_foreign_access_ref		= gnttab_end_foreign_access_ref_v1,
+	.end_foreign_transfer_ref	= gnttab_end_foreign_transfer_ref_v1,
+	.query_foreign_access		= gnttab_query_foreign_access_v1,
+};
+
+static struct gnttab_ops gnttab_v2_ops = {
+	.map_frames			= gnttab_map_frames_v2,
+	.unmap_frames			= gnttab_unmap_frames_v2,
+	.update_entry			= gnttab_update_entry_v2,
+	.end_foreign_access_ref		= gnttab_end_foreign_access_ref_v2,
+	.end_foreign_transfer_ref	= gnttab_end_foreign_transfer_ref_v2,
+	.query_foreign_access		= gnttab_query_foreign_access_v2,
+	.update_subpage_entry		= gnttab_update_subpage_entry_v2,
+	.update_trans_entry		= gnttab_update_trans_entry_v2,
+};
+
+static void gnttab_request_version(void)
+{
+	int rc;
+	struct gnttab_set_version gsv;
+
+	if (xen_hvm_domain())
+		gsv.version = 1;
+	else
+		gsv.version = 2;
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
+	if (rc == 0 && gsv.version == 2) {
+		grant_table_version = 2;
+		gnttab_interface = &gnttab_v2_ops;
+	} else if (grant_table_version == 2) {
+		/*
+		 * If we've already used version 2 features,
+		 * but then suddenly discover that they're not
+		 * available (e.g. migrating to an older
+		 * version of Xen), almost unbounded badness
+		 * can happen.
+		 */
+		panic("we need grant tables version 2, but only version 1 is available");
+	} else {
+		grant_table_version = 1;
+		gnttab_interface = &gnttab_v1_ops;
+	}
+	printk(KERN_INFO "Grant tables using version %d layout.\n",
+		grant_table_version);
+}
+
+int gnttab_resume(void)
+{
+	unsigned int max_nr_gframes;
+
+	gnttab_request_version();
+	max_nr_gframes = gnttab_max_grant_frames();
+	if (max_nr_gframes < nr_grant_frames)
+		return -ENOSYS;
+
+	if (xen_pv_domain())
+		return gnttab_map(0, nr_grant_frames - 1);
+
+	if (gnttab_shared.addr == NULL) {
+		gnttab_shared.addr = ioremap(xen_hvm_resume_frames,
+						PAGE_SIZE * max_nr_gframes);
+		if (gnttab_shared.addr == NULL) {
+			printk(KERN_WARNING
+					"Failed to ioremap gnttab share frames!");
+			return -ENOMEM;
+		}
+	}
+
+	gnttab_map(0, nr_grant_frames - 1);
+
+	return 0;
+}
+
+int gnttab_suspend(void)
+{
+	gnttab_interface->unmap_frames();
+	return 0;
+}
+
+static int gnttab_expand(unsigned int req_entries)
+{
+	int rc;
+	unsigned int cur, extra;
+
+	cur = nr_grant_frames;
+	extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
+		 GREFS_PER_GRANT_FRAME);
+	if (cur + extra > gnttab_max_grant_frames())
+		return -ENOSPC;
+
+	rc = gnttab_map(cur, cur + extra - 1);
+	if (rc == 0)
+		rc = grow_gnttab_list(extra);
+
+	return rc;
+}
+
+int gnttab_init(void)
+{
+	int i;
+	unsigned int max_nr_glist_frames, nr_glist_frames;
+	unsigned int nr_init_grefs;
+	int ret;
+
+	nr_grant_frames = 1;
+	boot_max_nr_grant_frames = __max_nr_grant_frames();
+
+	/* Determine the maximum number of frames required for the
+	 * grant reference free list on the current hypervisor.
+	 */
+	max_nr_glist_frames = (boot_max_nr_grant_frames *
+			       GREFS_PER_GRANT_FRAME / RPP);
+
+	gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
+			      GFP_KERNEL);
+	if (gnttab_list == NULL)
+		return -ENOMEM;
+
+	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+	for (i = 0; i < nr_glist_frames; i++) {
+		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
+		if (gnttab_list[i] == NULL) {
+			ret = -ENOMEM;
+			goto ini_nomem;
+		}
+	}
+
+	if (gnttab_resume() < 0) {
+		ret = -ENODEV;
+		goto ini_nomem;
+	}
+
+	nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
+
+	for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
+		gnttab_entry(i) = i + 1;
+
+	gnttab_entry(nr_init_grefs - 1) = GNTTAB_LIST_END;
+	gnttab_free_count = nr_init_grefs - NR_RESERVED_ENTRIES;
+	gnttab_free_head  = NR_RESERVED_ENTRIES;
+
+	printk("Grant table initialized\n");
+	return 0;
+
+ ini_nomem:
+	for (i--; i >= 0; i--)
+		free_page((unsigned long)gnttab_list[i]);
+	kfree(gnttab_list);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_init);
+
+static int __devinit __gnttab_init(void)
+{
+	/* Delay grant-table initialization in the PV on HVM case */
+	if (xen_hvm_domain())
+		return 0;
+
+	if (!xen_pv_domain())
+		return -ENODEV;
+
+	return gnttab_init();
+}
+
+core_initcall(__gnttab_init);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
new file mode 100644
index 00000000..412b96cc
--- /dev/null
+++ b/drivers/xen/manage.c
@@ -0,0 +1,339 @@
+/*
+ * Handle extern requests for shutdown, reboot and sysrq
+ */
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/reboot.h>
+#include <linux/sysrq.h>
+#include <linux/stop_machine.h>
+#include <linux/freezer.h>
+#include <linux/syscore_ops.h>
+#include <linux/export.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+#include <xen/hvc-console.h>
+#include <xen/xen-ops.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypervisor.h>
+
+enum shutdown_state {
+	SHUTDOWN_INVALID = -1,
+	SHUTDOWN_POWEROFF = 0,
+	SHUTDOWN_SUSPEND = 2,
+	/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
+	   report a crash, not be instructed to crash!
+	   HALT is the same as POWEROFF, as far as we're concerned.  The tools use
+	   the distinction when we return the reason code to them.  */
+	 SHUTDOWN_HALT = 4,
+};
+
+/* Ignore multiple shutdown requests. */
+static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
+
+struct suspend_info {
+	int cancelled;
+	unsigned long arg; /* extra hypercall argument */
+	void (*pre)(void);
+	void (*post)(int cancelled);
+};
+
+static void xen_hvm_post_suspend(int cancelled)
+{
+	xen_arch_hvm_post_suspend(cancelled);
+	gnttab_resume();
+}
+
+static void xen_pre_suspend(void)
+{
+	xen_mm_pin_all();
+	gnttab_suspend();
+	xen_arch_pre_suspend();
+}
+
+static void xen_post_suspend(int cancelled)
+{
+	xen_arch_post_suspend(cancelled);
+	gnttab_resume();
+	xen_mm_unpin_all();
+}
+
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+static int xen_suspend(void *data)
+{
+	struct suspend_info *si = data;
+	int err;
+
+	BUG_ON(!irqs_disabled());
+
+	err = syscore_suspend();
+	if (err) {
+		printk(KERN_ERR "xen_suspend: system core suspend failed: %d\n",
+			err);
+		return err;
+	}
+
+	if (si->pre)
+		si->pre();
+
+	/*
+	 * This hypercall returns 1 if suspend was cancelled
+	 * or the domain was merely checkpointed, and 0 if it
+	 * is resuming in a new domain.
+	 */
+	si->cancelled = HYPERVISOR_suspend(si->arg);
+
+	if (si->post)
+		si->post(si->cancelled);
+
+	if (!si->cancelled) {
+		xen_irq_resume();
+		xen_console_resume();
+		xen_timer_resume();
+	}
+
+	syscore_resume();
+
+	return 0;
+}
+
+static void do_suspend(void)
+{
+	int err;
+	struct suspend_info si;
+
+	shutting_down = SHUTDOWN_SUSPEND;
+
+#ifdef CONFIG_PREEMPT
+	/* If the kernel is preemptible, we need to freeze all the processes
+	   to prevent them from being in the middle of a pagetable update
+	   during suspend. */
+	err = freeze_processes();
+	if (err) {
+		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
+		goto out;
+	}
+#endif
+
+	err = dpm_suspend_start(PMSG_FREEZE);
+	if (err) {
+		printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", err);
+		goto out_thaw;
+	}
+
+	printk(KERN_DEBUG "suspending xenstore...\n");
+	xs_suspend();
+
+	err = dpm_suspend_end(PMSG_FREEZE);
+	if (err) {
+		printk(KERN_ERR "dpm_suspend_end failed: %d\n", err);
+		si.cancelled = 0;
+		goto out_resume;
+	}
+
+	si.cancelled = 1;
+
+	if (xen_hvm_domain()) {
+		si.arg = 0UL;
+		si.pre = NULL;
+		si.post = &xen_hvm_post_suspend;
+	} else {
+		si.arg = virt_to_mfn(xen_start_info);
+		si.pre = &xen_pre_suspend;
+		si.post = &xen_post_suspend;
+	}
+
+	err = stop_machine(xen_suspend, &si, cpumask_of(0));
+
+	dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
+
+	if (err) {
+		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
+		si.cancelled = 1;
+	}
+
+out_resume:
+	if (!si.cancelled) {
+		xen_arch_resume();
+		xs_resume();
+	} else
+		xs_suspend_cancel();
+
+	dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
+
+	/* Make sure timer events get retriggered on all CPUs */
+	clock_was_set();
+
+out_thaw:
+#ifdef CONFIG_PREEMPT
+	thaw_processes();
+out:
+#endif
+	shutting_down = SHUTDOWN_INVALID;
+}
+#endif	/* CONFIG_HIBERNATE_CALLBACKS */
+
+struct shutdown_handler {
+	const char *command;
+	void (*cb)(void);
+};
+
+static void do_poweroff(void)
+{
+	shutting_down = SHUTDOWN_POWEROFF;
+	orderly_poweroff(false);
+}
+
+static void do_reboot(void)
+{
+	shutting_down = SHUTDOWN_POWEROFF; /* ? */
+	ctrl_alt_del();
+}
+
+static void shutdown_handler(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len)
+{
+	char *str;
+	struct xenbus_transaction xbt;
+	int err;
+	static struct shutdown_handler handlers[] = {
+		{ "poweroff",	do_poweroff },
+		{ "halt",	do_poweroff },
+		{ "reboot",	do_reboot   },
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+		{ "suspend",	do_suspend  },
+#endif
+		{NULL, NULL},
+	};
+	static struct shutdown_handler *handler;
+
+	if (shutting_down != SHUTDOWN_INVALID)
+		return;
+
+ again:
+	err = xenbus_transaction_start(&xbt);
+	if (err)
+		return;
+
+	str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
+	/* Ignore read errors and empty reads. */
+	if (XENBUS_IS_ERR_READ(str)) {
+		xenbus_transaction_end(xbt, 1);
+		return;
+	}
+
+	for (handler = &handlers[0]; handler->command; handler++) {
+		if (strcmp(str, handler->command) == 0)
+			break;
+	}
+
+	/* Only acknowledge commands which we are prepared to handle. */
+	if (handler->cb)
+		xenbus_write(xbt, "control", "shutdown", "");
+
+	err = xenbus_transaction_end(xbt, 0);
+	if (err == -EAGAIN) {
+		kfree(str);
+		goto again;
+	}
+
+	if (handler->cb) {
+		handler->cb();
+	} else {
+		printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
+		shutting_down = SHUTDOWN_INVALID;
+	}
+
+	kfree(str);
+}
+
+#ifdef CONFIG_MAGIC_SYSRQ
+static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
+			  unsigned int len)
+{
+	char sysrq_key = '\0';
+	struct xenbus_transaction xbt;
+	int err;
+
+ again:
+	err = xenbus_transaction_start(&xbt);
+	if (err)
+		return;
+	if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) {
+		printk(KERN_ERR "Unable to read sysrq code in "
+		       "control/sysrq\n");
+		xenbus_transaction_end(xbt, 1);
+		return;
+	}
+
+	if (sysrq_key != '\0')
+		xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+
+	err = xenbus_transaction_end(xbt, 0);
+	if (err == -EAGAIN)
+		goto again;
+
+	if (sysrq_key != '\0')
+		handle_sysrq(sysrq_key);
+}
+
+static struct xenbus_watch sysrq_watch = {
+	.node = "control/sysrq",
+	.callback = sysrq_handler
+};
+#endif
+
+static struct xenbus_watch shutdown_watch = {
+	.node = "control/shutdown",
+	.callback = shutdown_handler
+};
+
+static int setup_shutdown_watcher(void)
+{
+	int err;
+
+	err = register_xenbus_watch(&shutdown_watch);
+	if (err) {
+		printk(KERN_ERR "Failed to set shutdown watcher\n");
+		return err;
+	}
+
+#ifdef CONFIG_MAGIC_SYSRQ
+	err = register_xenbus_watch(&sysrq_watch);
+	if (err) {
+		printk(KERN_ERR "Failed to set sysrq watcher\n");
+		return err;
+	}
+#endif
+
+	return 0;
+}
+
+static int shutdown_event(struct notifier_block *notifier,
+			  unsigned long event,
+			  void *data)
+{
+	setup_shutdown_watcher();
+	return NOTIFY_DONE;
+}
+
+int xen_setup_shutdown_event(void)
+{
+	static struct notifier_block xenstore_notifier = {
+		.notifier_call = shutdown_event
+	};
+
+	if (!xen_domain())
+		return -ENODEV;
+	register_xenstore_notifier(&xenstore_notifier);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
+
+subsys_initcall(xen_setup_shutdown_event);
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
new file mode 100644
index 00000000..b84bf0b6
--- /dev/null
+++ b/drivers/xen/pci.c
@@ -0,0 +1,194 @@
+/*
+ * Copyright (c) 2009, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Weidong Han <weidong.han@intel.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <xen/xen.h>
+#include <xen/interface/physdev.h>
+#include <xen/interface/xen.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include "../pci/pci.h"
+
+static bool __read_mostly pci_seg_supported = true;
+
+static int xen_add_device(struct device *dev)
+{
+	int r;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+#ifdef CONFIG_PCI_IOV
+	struct pci_dev *physfn = pci_dev->physfn;
+#endif
+
+	if (pci_seg_supported) {
+		struct physdev_pci_device_add add = {
+			.seg = pci_domain_nr(pci_dev->bus),
+			.bus = pci_dev->bus->number,
+			.devfn = pci_dev->devfn
+		};
+#ifdef CONFIG_ACPI
+		acpi_handle handle;
+#endif
+
+#ifdef CONFIG_PCI_IOV
+		if (pci_dev->is_virtfn) {
+			add.flags = XEN_PCI_DEV_VIRTFN;
+			add.physfn.bus = physfn->bus->number;
+			add.physfn.devfn = physfn->devfn;
+		} else
+#endif
+		if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn))
+			add.flags = XEN_PCI_DEV_EXTFN;
+
+#ifdef CONFIG_ACPI
+		handle = DEVICE_ACPI_HANDLE(&pci_dev->dev);
+		if (!handle)
+			handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge);
+#ifdef CONFIG_PCI_IOV
+		if (!handle && pci_dev->is_virtfn)
+			handle = DEVICE_ACPI_HANDLE(physfn->bus->bridge);
+#endif
+		if (handle) {
+			acpi_status status;
+
+			do {
+				unsigned long long pxm;
+
+				status = acpi_evaluate_integer(handle, "_PXM",
+							       NULL, &pxm);
+				if (ACPI_SUCCESS(status)) {
+					add.optarr[0] = pxm;
+					add.flags |= XEN_PCI_DEV_PXM;
+					break;
+				}
+				status = acpi_get_parent(handle, &handle);
+			} while (ACPI_SUCCESS(status));
+		}
+#endif /* CONFIG_ACPI */
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_add, &add);
+		if (r != -ENOSYS)
+			return r;
+		pci_seg_supported = false;
+	}
+
+	if (pci_domain_nr(pci_dev->bus))
+		r = -ENOSYS;
+#ifdef CONFIG_PCI_IOV
+	else if (pci_dev->is_virtfn) {
+		struct physdev_manage_pci_ext manage_pci_ext = {
+			.bus		= pci_dev->bus->number,
+			.devfn		= pci_dev->devfn,
+			.is_virtfn 	= 1,
+			.physfn.bus	= physfn->bus->number,
+			.physfn.devfn	= physfn->devfn,
+		};
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext,
+			&manage_pci_ext);
+	}
+#endif
+	else if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) {
+		struct physdev_manage_pci_ext manage_pci_ext = {
+			.bus		= pci_dev->bus->number,
+			.devfn		= pci_dev->devfn,
+			.is_extfn	= 1,
+		};
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext,
+			&manage_pci_ext);
+	} else {
+		struct physdev_manage_pci manage_pci = {
+			.bus	= pci_dev->bus->number,
+			.devfn	= pci_dev->devfn,
+		};
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add,
+			&manage_pci);
+	}
+
+	return r;
+}
+
+static int xen_remove_device(struct device *dev)
+{
+	int r;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
+	if (pci_seg_supported) {
+		struct physdev_pci_device device = {
+			.seg = pci_domain_nr(pci_dev->bus),
+			.bus = pci_dev->bus->number,
+			.devfn = pci_dev->devfn
+		};
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_remove,
+					  &device);
+	} else if (pci_domain_nr(pci_dev->bus))
+		r = -ENOSYS;
+	else {
+		struct physdev_manage_pci manage_pci = {
+			.bus = pci_dev->bus->number,
+			.devfn = pci_dev->devfn
+		};
+
+		r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove,
+					  &manage_pci);
+	}
+
+	return r;
+}
+
+static int xen_pci_notifier(struct notifier_block *nb,
+			    unsigned long action, void *data)
+{
+	struct device *dev = data;
+	int r = 0;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		r = xen_add_device(dev);
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		r = xen_remove_device(dev);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+	if (r)
+		dev_err(dev, "Failed to %s - passthrough or MSI/MSI-X might fail!\n",
+			action == BUS_NOTIFY_ADD_DEVICE ? "add" :
+			(action == BUS_NOTIFY_DEL_DEVICE ? "delete" : "?"));
+	return NOTIFY_OK;
+}
+
+static struct notifier_block device_nb = {
+	.notifier_call = xen_pci_notifier,
+};
+
+static int __init register_xen_pci_notifier(void)
+{
+	if (!xen_initial_domain())
+		return 0;
+
+	return bus_register_notifier(&pci_bus_type, &device_nb);
+}
+
+arch_initcall(register_xen_pci_notifier);
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
new file mode 100644
index 00000000..2389e581
--- /dev/null
+++ b/drivers/xen/platform-pci.c
@@ -0,0 +1,192 @@
+/******************************************************************************
+ * platform-pci.c
+ *
+ * Xen platform PCI device driver
+ * Copyright (c) 2005, Intel Corporation.
+ * Copyright (c) 2007, XenSource Inc.
+ * Copyright (c) 2010, Citrix
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <xen/platform_pci.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/hvm.h>
+#include <xen/xen-ops.h>
+
+#define DRV_NAME    "xen-platform-pci"
+
+MODULE_AUTHOR("ssmith@xensource.com and stefano.stabellini@eu.citrix.com");
+MODULE_DESCRIPTION("Xen platform PCI device");
+MODULE_LICENSE("GPL");
+
+static unsigned long platform_mmio;
+static unsigned long platform_mmio_alloc;
+static unsigned long platform_mmiolen;
+static uint64_t callback_via;
+
+unsigned long alloc_xen_mmio(unsigned long len)
+{
+	unsigned long addr;
+
+	addr = platform_mmio + platform_mmio_alloc;
+	platform_mmio_alloc += len;
+	BUG_ON(platform_mmio_alloc > platform_mmiolen);
+
+	return addr;
+}
+
+static uint64_t get_callback_via(struct pci_dev *pdev)
+{
+	u8 pin;
+	int irq;
+
+	irq = pdev->irq;
+	if (irq < 16)
+		return irq; /* ISA IRQ */
+
+	pin = pdev->pin;
+
+	/* We don't know the GSI. Specify the PCI INTx line instead. */
+	return ((uint64_t)0x01 << 56) | /* PCI INTx identifier */
+		((uint64_t)pci_domain_nr(pdev->bus) << 32) |
+		((uint64_t)pdev->bus->number << 16) |
+		((uint64_t)(pdev->devfn & 0xff) << 8) |
+		((uint64_t)(pin - 1) & 3);
+}
+
+static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id)
+{
+	xen_hvm_evtchn_do_upcall();
+	return IRQ_HANDLED;
+}
+
+static int xen_allocate_irq(struct pci_dev *pdev)
+{
+	return request_irq(pdev->irq, do_hvm_evtchn_intr,
+			IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
+			"xen-platform-pci", pdev);
+}
+
+static int platform_pci_resume(struct pci_dev *pdev)
+{
+	int err;
+	if (xen_have_vector_callback)
+		return 0;
+	err = xen_set_callback_via(callback_via);
+	if (err) {
+		dev_err(&pdev->dev, "platform_pci_resume failure!\n");
+		return err;
+	}
+	return 0;
+}
+
+static int __devinit platform_pci_init(struct pci_dev *pdev,
+				       const struct pci_device_id *ent)
+{
+	int i, ret;
+	long ioaddr;
+	long mmio_addr, mmio_len;
+	unsigned int max_nr_gframes;
+
+	i = pci_enable_device(pdev);
+	if (i)
+		return i;
+
+	ioaddr = pci_resource_start(pdev, 0);
+
+	mmio_addr = pci_resource_start(pdev, 1);
+	mmio_len = pci_resource_len(pdev, 1);
+
+	if (mmio_addr == 0 || ioaddr == 0) {
+		dev_err(&pdev->dev, "no resources found\n");
+		ret = -ENOENT;
+		goto pci_out;
+	}
+
+	ret = pci_request_region(pdev, 1, DRV_NAME);
+	if (ret < 0)
+		goto pci_out;
+
+	ret = pci_request_region(pdev, 0, DRV_NAME);
+	if (ret < 0)
+		goto mem_out;
+
+	platform_mmio = mmio_addr;
+	platform_mmiolen = mmio_len;
+
+	if (!xen_have_vector_callback) {
+		ret = xen_allocate_irq(pdev);
+		if (ret) {
+			dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
+			goto out;
+		}
+		callback_via = get_callback_via(pdev);
+		ret = xen_set_callback_via(callback_via);
+		if (ret) {
+			dev_warn(&pdev->dev, "Unable to set the evtchn callback "
+					 "err=%d\n", ret);
+			goto out;
+		}
+	}
+
+	max_nr_gframes = gnttab_max_grant_frames();
+	xen_hvm_resume_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes);
+	ret = gnttab_init();
+	if (ret)
+		goto out;
+	xenbus_probe(NULL);
+	return 0;
+
+out:
+	pci_release_region(pdev, 0);
+mem_out:
+	pci_release_region(pdev, 1);
+pci_out:
+	pci_disable_device(pdev);
+	return ret;
+}
+
+static struct pci_device_id platform_pci_tbl[] __devinitdata = {
+	{PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
+	{0,}
+};
+
+MODULE_DEVICE_TABLE(pci, platform_pci_tbl);
+
+static struct pci_driver platform_driver = {
+	.name =           DRV_NAME,
+	.probe =          platform_pci_init,
+	.id_table =       platform_pci_tbl,
+#ifdef CONFIG_PM
+	.resume_early =   platform_pci_resume,
+#endif
+};
+
+static int __init platform_pci_module_init(void)
+{
+	return pci_register_driver(&platform_driver);
+}
+
+module_init(platform_pci_module_init);
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
new file mode 100644
index 00000000..ccee0f16
--- /dev/null
+++ b/drivers/xen/privcmd.c
@@ -0,0 +1,435 @@
+/******************************************************************************
+ * privcmd.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002-2004, K A Fraser, B Dragovic
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/uaccess.h>
+#include <linux/swap.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/privcmd.h>
+#include <xen/interface/xen.h>
+#include <xen/features.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+
+#include "privcmd.h"
+
+MODULE_LICENSE("GPL");
+
+#ifndef HAVE_ARCH_PRIVCMD_MMAP
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma);
+#endif
+
+static long privcmd_ioctl_hypercall(void __user *udata)
+{
+	struct privcmd_hypercall hypercall;
+	long ret;
+
+	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
+		return -EFAULT;
+
+	ret = privcmd_call(hypercall.op,
+			   hypercall.arg[0], hypercall.arg[1],
+			   hypercall.arg[2], hypercall.arg[3],
+			   hypercall.arg[4]);
+
+	return ret;
+}
+
+static void free_page_list(struct list_head *pages)
+{
+	struct page *p, *n;
+
+	list_for_each_entry_safe(p, n, pages, lru)
+		__free_page(p);
+
+	INIT_LIST_HEAD(pages);
+}
+
+/*
+ * Given an array of items in userspace, return a list of pages
+ * containing the data.  If copying fails, either because of memory
+ * allocation failure or a problem reading user memory, return an
+ * error code; its up to the caller to dispose of any partial list.
+ */
+static int gather_array(struct list_head *pagelist,
+			unsigned nelem, size_t size,
+			void __user *data)
+{
+	unsigned pageidx;
+	void *pagedata;
+	int ret;
+
+	if (size > PAGE_SIZE)
+		return 0;
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* quiet, gcc */
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page = alloc_page(GFP_KERNEL);
+
+			ret = -ENOMEM;
+			if (page == NULL)
+				goto fail;
+
+			pagedata = page_address(page);
+
+			list_add_tail(&page->lru, pagelist);
+			pageidx = 0;
+		}
+
+		ret = -EFAULT;
+		if (copy_from_user(pagedata + pageidx, data, size))
+			goto fail;
+
+		data += size;
+		pageidx += size;
+	}
+
+	ret = 0;
+
+fail:
+	return ret;
+}
+
+/*
+ * Call function "fn" on each element of the array fragmented
+ * over a list of pages.
+ */
+static int traverse_pages(unsigned nelem, size_t size,
+			  struct list_head *pos,
+			  int (*fn)(void *data, void *state),
+			  void *state)
+{
+	void *pagedata;
+	unsigned pageidx;
+	int ret = 0;
+
+	BUG_ON(size > PAGE_SIZE);
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* hush, gcc */
+
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page;
+			pos = pos->next;
+			page = list_entry(pos, struct page, lru);
+			pagedata = page_address(page);
+			pageidx = 0;
+		}
+
+		ret = (*fn)(pagedata + pageidx, state);
+		if (ret)
+			break;
+		pageidx += size;
+	}
+
+	return ret;
+}
+
+struct mmap_mfn_state {
+	unsigned long va;
+	struct vm_area_struct *vma;
+	domid_t domain;
+};
+
+static int mmap_mfn_range(void *data, void *state)
+{
+	struct privcmd_mmap_entry *msg = data;
+	struct mmap_mfn_state *st = state;
+	struct vm_area_struct *vma = st->vma;
+	int rc;
+
+	/* Do not allow range to wrap the address space. */
+	if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) ||
+	    ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va))
+		return -EINVAL;
+
+	/* Range chunks must be contiguous in va space. */
+	if ((msg->va != st->va) ||
+	    ((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end))
+		return -EINVAL;
+
+	rc = xen_remap_domain_mfn_range(vma,
+					msg->va & PAGE_MASK,
+					msg->mfn, msg->npages,
+					vma->vm_page_prot,
+					st->domain);
+	if (rc < 0)
+		return rc;
+
+	st->va += msg->npages << PAGE_SHIFT;
+
+	return 0;
+}
+
+static long privcmd_ioctl_mmap(void __user *udata)
+{
+	struct privcmd_mmap mmapcmd;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
+	LIST_HEAD(pagelist);
+	struct mmap_mfn_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
+		return -EFAULT;
+
+	rc = gather_array(&pagelist,
+			  mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			  mmapcmd.entry);
+
+	if (rc || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	{
+		struct page *page = list_first_entry(&pagelist,
+						     struct page, lru);
+		struct privcmd_mmap_entry *msg = page_address(page);
+
+		vma = find_vma(mm, msg->va);
+		rc = -EINVAL;
+
+		if (!vma || (msg->va != vma->vm_start) ||
+		    !privcmd_enforce_singleshot_mapping(vma))
+			goto out_up;
+	}
+
+	state.va = vma->vm_start;
+	state.vma = vma;
+	state.domain = mmapcmd.dom;
+
+	rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			    &pagelist,
+			    mmap_mfn_range, &state);
+
+
+out_up:
+	up_write(&mm->mmap_sem);
+
+out:
+	free_page_list(&pagelist);
+
+	return rc;
+}
+
+struct mmap_batch_state {
+	domid_t domain;
+	unsigned long va;
+	struct vm_area_struct *vma;
+	int err;
+
+	xen_pfn_t __user *user;
+};
+
+static int mmap_batch_fn(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
+				       st->vma->vm_page_prot, st->domain) < 0) {
+		*mfnp |= 0xf0000000U;
+		st->err++;
+	}
+	st->va += PAGE_SIZE;
+
+	return 0;
+}
+
+static int mmap_return_errors(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	return put_user(*mfnp, st->user++);
+}
+
+static struct vm_operations_struct privcmd_vm_ops;
+
+static long privcmd_ioctl_mmap_batch(void __user *udata)
+{
+	int ret;
+	struct privcmd_mmapbatch m;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long nr_pages;
+	LIST_HEAD(pagelist);
+	struct mmap_batch_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&m, udata, sizeof(m)))
+		return -EFAULT;
+
+	nr_pages = m.num;
+	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
+		return -EINVAL;
+
+	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t),
+			   m.arr);
+
+	if (ret || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	vma = find_vma(mm, m.addr);
+	ret = -EINVAL;
+	if (!vma ||
+	    vma->vm_ops != &privcmd_vm_ops ||
+	    (m.addr != vma->vm_start) ||
+	    ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) ||
+	    !privcmd_enforce_singleshot_mapping(vma)) {
+		up_write(&mm->mmap_sem);
+		goto out;
+	}
+
+	state.domain = m.dom;
+	state.vma = vma;
+	state.va = m.addr;
+	state.err = 0;
+
+	ret = traverse_pages(m.num, sizeof(xen_pfn_t),
+			     &pagelist, mmap_batch_fn, &state);
+
+	up_write(&mm->mmap_sem);
+
+	if (state.err > 0) {
+		state.user = m.arr;
+		ret = traverse_pages(m.num, sizeof(xen_pfn_t),
+			       &pagelist,
+			       mmap_return_errors, &state);
+	}
+
+out:
+	free_page_list(&pagelist);
+
+	return ret;
+}
+
+static long privcmd_ioctl(struct file *file,
+			  unsigned int cmd, unsigned long data)
+{
+	int ret = -ENOSYS;
+	void __user *udata = (void __user *) data;
+
+	switch (cmd) {
+	case IOCTL_PRIVCMD_HYPERCALL:
+		ret = privcmd_ioctl_hypercall(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAP:
+		ret = privcmd_ioctl_mmap(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAPBATCH:
+		ret = privcmd_ioctl_mmap_batch(udata);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+	       vma, vma->vm_start, vma->vm_end,
+	       vmf->pgoff, vmf->virtual_address);
+
+	return VM_FAULT_SIGBUS;
+}
+
+static struct vm_operations_struct privcmd_vm_ops = {
+	.fault = privcmd_fault
+};
+
+static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* Unsupported for auto-translate guests. */
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -ENOSYS;
+
+	/* DONTCOPY is essential for Xen because copy_page_range doesn't know
+	 * how to recreate these mappings */
+	vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY | VM_PFNMAP;
+	vma->vm_ops = &privcmd_vm_ops;
+	vma->vm_private_data = NULL;
+
+	return 0;
+}
+
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma)
+{
+	return (xchg(&vma->vm_private_data, (void *)1) == NULL);
+}
+
+const struct file_operations xen_privcmd_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = privcmd_ioctl,
+	.mmap = privcmd_mmap,
+};
+EXPORT_SYMBOL_GPL(xen_privcmd_fops);
+
+static struct miscdevice privcmd_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "xen/privcmd",
+	.fops = &xen_privcmd_fops,
+};
+
+static int __init privcmd_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	err = misc_register(&privcmd_dev);
+	if (err != 0) {
+		printk(KERN_ERR "Could not register Xen privcmd device\n");
+		return err;
+	}
+	return 0;
+}
+
+static void __exit privcmd_exit(void)
+{
+	misc_deregister(&privcmd_dev);
+}
+
+module_init(privcmd_init);
+module_exit(privcmd_exit);
diff --git a/drivers/xen/privcmd.h b/drivers/xen/privcmd.h
new file mode 100644
index 00000000..14facaee
--- /dev/null
+++ b/drivers/xen/privcmd.h
@@ -0,0 +1,3 @@
+#include <linux/fs.h>
+
+extern const struct file_operations xen_privcmd_fops;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
new file mode 100644
index 00000000..1afb4fba
--- /dev/null
+++ b/drivers/xen/swiotlb-xen.c
@@ -0,0 +1,559 @@
+/*
+ *  Copyright 2010
+ *  by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ *
+ * This code provides a IOMMU for Xen PV guests with PCI passthrough.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * PV guests under Xen are running in an non-contiguous memory architecture.
+ *
+ * When PCI pass-through is utilized, this necessitates an IOMMU for
+ * translating bus (DMA) to virtual and vice-versa and also providing a
+ * mechanism to have contiguous pages for device drivers operations (say DMA
+ * operations).
+ *
+ * Specifically, under Xen the Linux idea of pages is an illusion. It
+ * assumes that pages start at zero and go up to the available memory. To
+ * help with that, the Linux Xen MMU provides a lookup mechanism to
+ * translate the page frame numbers (PFN) to machine frame numbers (MFN)
+ * and vice-versa. The MFN are the "real" frame numbers. Furthermore
+ * memory is not contiguous. Xen hypervisor stitches memory for guests
+ * from different pools, which means there is no guarantee that PFN==MFN
+ * and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
+ * allocated in descending order (high to low), meaning the guest might
+ * never get any MFN's under the 4GB mark.
+ *
+ */
+
+#include <linux/bootmem.h>
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <xen/swiotlb-xen.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+#include <xen/hvc-console.h>
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+
+static char *xen_io_tlb_start, *xen_io_tlb_end;
+static unsigned long xen_io_tlb_nslabs;
+/*
+ * Quick lookup value of the bus address of the IOTLB.
+ */
+
+u64 start_dma_addr;
+
+static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+{
+	return phys_to_machine(XPADDR(paddr)).maddr;
+}
+
+static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
+{
+	return machine_to_phys(XMADDR(baddr)).paddr;
+}
+
+static dma_addr_t xen_virt_to_bus(void *address)
+{
+	return xen_phys_to_bus(virt_to_phys(address));
+}
+
+static int check_pages_physically_contiguous(unsigned long pfn,
+					     unsigned int offset,
+					     size_t length)
+{
+	unsigned long next_mfn;
+	int i;
+	int nr_pages;
+
+	next_mfn = pfn_to_mfn(pfn);
+	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
+
+	for (i = 1; i < nr_pages; i++) {
+		if (pfn_to_mfn(++pfn) != ++next_mfn)
+			return 0;
+	}
+	return 1;
+}
+
+static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+{
+	unsigned long pfn = PFN_DOWN(p);
+	unsigned int offset = p & ~PAGE_MASK;
+
+	if (offset + size <= PAGE_SIZE)
+		return 0;
+	if (check_pages_physically_contiguous(pfn, offset, size))
+		return 0;
+	return 1;
+}
+
+static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
+{
+	unsigned long mfn = PFN_DOWN(dma_addr);
+	unsigned long pfn = mfn_to_local_pfn(mfn);
+	phys_addr_t paddr;
+
+	/* If the address is outside our domain, it CAN
+	 * have the same virtual address as another address
+	 * in our domain. Therefore _only_ check address within our domain.
+	 */
+	if (pfn_valid(pfn)) {
+		paddr = PFN_PHYS(pfn);
+		return paddr >= virt_to_phys(xen_io_tlb_start) &&
+		       paddr < virt_to_phys(xen_io_tlb_end);
+	}
+	return 0;
+}
+
+static int max_dma_bits = 32;
+
+static int
+xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+{
+	int i, rc;
+	int dma_bits;
+
+	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+
+	i = 0;
+	do {
+		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
+
+		do {
+			rc = xen_create_contiguous_region(
+				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				get_order(slabs << IO_TLB_SHIFT),
+				dma_bits);
+		} while (rc && dma_bits++ < max_dma_bits);
+		if (rc)
+			return rc;
+
+		i += slabs;
+	} while (i < nslabs);
+	return 0;
+}
+
+void __init xen_swiotlb_init(int verbose)
+{
+	unsigned long bytes;
+	int rc = -ENOMEM;
+	unsigned long nr_tbl;
+	char *m = NULL;
+	unsigned int repeat = 3;
+
+	nr_tbl = swiotlb_nr_tbl();
+	if (nr_tbl)
+		xen_io_tlb_nslabs = nr_tbl;
+	else {
+		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+retry:
+	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from any location.
+	 */
+	xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	if (!xen_io_tlb_start) {
+		m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+		goto error;
+	}
+	xen_io_tlb_end = xen_io_tlb_start + bytes;
+	/*
+	 * And replace that memory with pages under 4GB.
+	 */
+	rc = xen_swiotlb_fixup(xen_io_tlb_start,
+			       bytes,
+			       xen_io_tlb_nslabs);
+	if (rc) {
+		free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		m = "Failed to get contiguous memory for DMA from Xen!\n"\
+		    "You either: don't have the permissions, do not have"\
+		    " enough free memory under 4GB, or the hypervisor memory"\
+		    "is too fragmented!";
+		goto error;
+	}
+	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
+	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+
+	return;
+error:
+	if (repeat--) {
+		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
+					(xen_io_tlb_nslabs >> 1));
+		printk(KERN_INFO "Xen-SWIOTLB: Lowering to %luMB\n",
+		      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
+		goto retry;
+	}
+	xen_raw_printk("%s (rc:%d)", m, rc);
+	panic("%s (rc:%d)", m, rc);
+}
+
+void *
+xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags,
+			   struct dma_attrs *attrs)
+{
+	void *ret;
+	int order = get_order(size);
+	u64 dma_mask = DMA_BIT_MASK(32);
+	unsigned long vstart;
+	phys_addr_t phys;
+	dma_addr_t dev_addr;
+
+	/*
+	* Ignore region specifiers - the kernel's ideas of
+	* pseudo-phys memory layout has nothing to do with the
+	* machine physical layout.  We can't allocate highmem
+	* because we can't return a pointer to it.
+	*/
+	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
+		return ret;
+
+	vstart = __get_free_pages(flags, order);
+	ret = (void *)vstart;
+
+	if (!ret)
+		return ret;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = hwdev->coherent_dma_mask;
+
+	phys = virt_to_phys(ret);
+	dev_addr = xen_phys_to_bus(phys);
+	if (((dev_addr + size - 1 <= dma_mask)) &&
+	    !range_straddles_page_boundary(phys, size))
+		*dma_handle = dev_addr;
+	else {
+		if (xen_create_contiguous_region(vstart, order,
+						 fls64(dma_mask)) != 0) {
+			free_pages(vstart, order);
+			return NULL;
+		}
+		*dma_handle = virt_to_machine(ret).maddr;
+	}
+	memset(ret, 0, size);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
+
+void
+xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+			  dma_addr_t dev_addr, struct dma_attrs *attrs)
+{
+	int order = get_order(size);
+	phys_addr_t phys;
+	u64 dma_mask = DMA_BIT_MASK(32);
+
+	if (dma_release_from_coherent(hwdev, order, vaddr))
+		return;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = hwdev->coherent_dma_mask;
+
+	phys = virt_to_phys(vaddr);
+
+	if (((dev_addr + size - 1 > dma_mask)) ||
+	    range_straddles_page_boundary(phys, size))
+		xen_destroy_contiguous_region((unsigned long)vaddr, order);
+
+	free_pages((unsigned long)vaddr, order);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
+
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode.  The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dev_addr = xen_phys_to_bus(phys);
+	void *map;
+
+	BUG_ON(dir == DMA_NONE);
+	/*
+	 * If the address happens to be in the device's DMA window,
+	 * we can safely return the device addr and not worry about bounce
+	 * buffering it.
+	 */
+	if (dma_capable(dev, dev_addr, size) &&
+	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+		return dev_addr;
+
+	/*
+	 * Oh well, have to allocate and map a bounce buffer.
+	 */
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
+	if (!map)
+		return DMA_ERROR_CODE;
+
+	dev_addr = xen_virt_to_bus(map);
+
+	/*
+	 * Ensure that the address returned is DMA'ble
+	 */
+	if (!dma_capable(dev, dev_addr, size)) {
+		swiotlb_tbl_unmap_single(dev, map, size, dir);
+		dev_addr = 0;
+	}
+	return dev_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
+
+/*
+ * Unmap a single streaming mode DMA translation.  The dma_addr and size must
+ * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	xen_unmap_single(hwdev, dev_addr, size, dir);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so.  At the next point you give the dma
+ * address back to the card, you must first perform a
+ * xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			enum dma_sync_target target)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
+				       target);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
+
+void
+xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above xen_swiotlb_map_page
+ * interface.  Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length.  They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ *       DMA address/length pairs than there are SG table elements.
+ *       (for example via virtual mapping capabilities)
+ *       The routine returns the number of addr/length pairs actually
+ *       used, at most nents.
+ *
+ * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
+ * same here.
+ */
+int
+xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			 int nelems, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i) {
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
+
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length) ||
+		    range_straddles_page_boundary(paddr, sg->length)) {
+			void *map = swiotlb_tbl_map_single(hwdev,
+							   start_dma_addr,
+							   sg_phys(sg),
+							   sg->length, dir);
+			if (!map) {
+				/* Don't panic here, we expect map_sg users
+				   to do proper error handling. */
+				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+							   attrs);
+				sgl[0].dma_length = 0;
+				return DMA_ERROR_CODE;
+			}
+			sg->dma_address = xen_virt_to_bus(map);
+		} else
+			sg->dma_address = dev_addr;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
+
+int
+xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		   enum dma_data_direction dir)
+{
+	return xen_swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg);
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
+
+void
+xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		     enum dma_data_direction dir)
+{
+	return xen_swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg);
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+		    int nelems, enum dma_data_direction dir,
+		    enum dma_sync_target target)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_swiotlb_sync_single(hwdev, sg->dma_address,
+					sg->dma_length, dir, target);
+}
+
+void
+xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
+
+void
+xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			       int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
+
+int
+xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);
diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
new file mode 100644
index 00000000..fdb6d229
--- /dev/null
+++ b/drivers/xen/sys-hypervisor.c
@@ -0,0 +1,447 @@
+/*
+ *  copyright (c) 2006 IBM Corporation
+ *  Authored by: Mike D. Day <ncmike@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr  _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = \
+	__ATTR(_name, 0644, _name##_show, _name##_store)
+
+struct hyp_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+	ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+	void *hyp_attr_data;
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static void xen_sysfs_type_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version >> 16);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version & 0xff);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *extra;
+
+	extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+	if (extra) {
+		ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", extra);
+		kfree(extra);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+	&major_attr.attr,
+	&minor_attr.attr,
+	&extra_attr.attr,
+	NULL
+};
+
+static const struct attribute_group version_group = {
+	.name = "version",
+	.attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+static void xen_sysfs_version_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	char *vm, *val;
+	int ret;
+	extern int xenstored_ready;
+
+	if (!xenstored_ready)
+		return -EBUSY;
+
+	vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+	if (IS_ERR(vm))
+		return PTR_ERR(vm);
+	val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+	kfree(vm);
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+	ret = sprintf(buffer, "%s\n", val);
+	kfree(val);
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+static void xen_sysfs_uuid_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compiler);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_by);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_date);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+	&compiler_attr.attr,
+	&compiled_by_attr.attr,
+	&compile_date_attr.attr,
+	NULL
+};
+
+static const struct attribute_group xen_compilation_group = {
+	.name = "compilation",
+	.attrs = xen_compile_attrs,
+};
+
+static int __init xen_compilation_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+static void xen_compilation_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *caps;
+
+	caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+	if (caps) {
+		ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", caps);
+		kfree(caps);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *cset;
+
+	cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+	if (cset) {
+		ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", cset);
+		kfree(cset);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_platform_parameters *parms;
+
+	parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+	if (parms) {
+		ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+					     parms);
+		if (!ret)
+			ret = sprintf(buffer, "%lx\n", parms->virt_start);
+		kfree(parms);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+
+	ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+	if (ret > 0)
+		ret = sprintf(buffer, "%x\n", ret);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+	ssize_t ret;
+	struct xen_feature_info info;
+
+	info.submap_idx = index;
+	ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+	if (!ret)
+		ret = sprintf(buffer, "%08x", info.submap);
+
+	return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t len;
+	int i;
+
+	len = 0;
+	for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+		int ret = xen_feature_show(i, buffer + len);
+		if (ret < 0) {
+			if (len == 0)
+				len = ret;
+			break;
+		}
+		len += ret;
+	}
+	if (len > 0)
+		buffer[len++] = '\n';
+
+	return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static struct attribute *xen_properties_attrs[] = {
+	&capabilities_attr.attr,
+	&changeset_attr.attr,
+	&virtual_start_attr.attr,
+	&pagesize_attr.attr,
+	&features_attr.attr,
+	NULL
+};
+
+static const struct attribute_group xen_properties_group = {
+	.name = "properties",
+	.attrs = xen_properties_attrs,
+};
+
+static int __init xen_properties_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static void xen_properties_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static int __init hyper_sysfs_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	ret = xen_sysfs_type_init();
+	if (ret)
+		goto out;
+	ret = xen_sysfs_version_init();
+	if (ret)
+		goto version_out;
+	ret = xen_compilation_init();
+	if (ret)
+		goto comp_out;
+	ret = xen_sysfs_uuid_init();
+	if (ret)
+		goto uuid_out;
+	ret = xen_properties_init();
+	if (ret)
+		goto prop_out;
+
+	goto out;
+
+prop_out:
+	xen_sysfs_uuid_destroy();
+uuid_out:
+	xen_compilation_destroy();
+comp_out:
+	xen_sysfs_version_destroy();
+version_out:
+	xen_sysfs_type_destroy();
+out:
+	return ret;
+}
+
+static void __exit hyper_sysfs_exit(void)
+{
+	xen_properties_destroy();
+	xen_compilation_destroy();
+	xen_sysfs_uuid_destroy();
+	xen_sysfs_version_destroy();
+	xen_sysfs_type_destroy();
+
+}
+module_init(hyper_sysfs_init);
+module_exit(hyper_sysfs_exit);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+			      struct attribute *attr,
+			      char *buffer)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->show)
+		return hyp_attr->show(hyp_attr, buffer);
+	return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buffer,
+			       size_t len)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->store)
+		return hyp_attr->store(hyp_attr, buffer, len);
+	return 0;
+}
+
+static const struct sysfs_ops hyp_sysfs_ops = {
+	.show = hyp_sysfs_show,
+	.store = hyp_sysfs_store,
+};
+
+static struct kobj_type hyp_sysfs_kobj_type = {
+	.sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+	return 0;
+}
+device_initcall(hypervisor_subsys_init);
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
new file mode 100644
index 00000000..dcb79521
--- /dev/null
+++ b/drivers/xen/tmem.c
@@ -0,0 +1,405 @@
+/*
+ * Xen implementation for transcendent memory (tmem)
+ *
+ * Copyright (C) 2009-2011 Oracle Corp.  All rights reserved.
+ * Author: Dan Magenheimer
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/cleancache.h>
+
+/* temporary ifdef until include/linux/frontswap.h is upstream */
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+#endif
+
+#include <xen/xen.h>
+#include <xen/interface/xen.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypervisor.h>
+
+#define TMEM_CONTROL               0
+#define TMEM_NEW_POOL              1
+#define TMEM_DESTROY_POOL          2
+#define TMEM_NEW_PAGE              3
+#define TMEM_PUT_PAGE              4
+#define TMEM_GET_PAGE              5
+#define TMEM_FLUSH_PAGE            6
+#define TMEM_FLUSH_OBJECT          7
+#define TMEM_READ                  8
+#define TMEM_WRITE                 9
+#define TMEM_XCHG                 10
+
+/* Bits for HYPERVISOR_tmem_op(TMEM_NEW_POOL) */
+#define TMEM_POOL_PERSIST          1
+#define TMEM_POOL_SHARED           2
+#define TMEM_POOL_PAGESIZE_SHIFT   4
+#define TMEM_VERSION_SHIFT        24
+
+
+struct tmem_pool_uuid {
+	u64 uuid_lo;
+	u64 uuid_hi;
+};
+
+struct tmem_oid {
+	u64 oid[3];
+};
+
+#define TMEM_POOL_PRIVATE_UUID	{ 0, 0 }
+
+/* flags for tmem_ops.new_pool */
+#define TMEM_POOL_PERSIST          1
+#define TMEM_POOL_SHARED           2
+
+/* xen tmem foundation ops/hypercalls */
+
+static inline int xen_tmem_op(u32 tmem_cmd, u32 tmem_pool, struct tmem_oid oid,
+	u32 index, unsigned long gmfn, u32 tmem_offset, u32 pfn_offset, u32 len)
+{
+	struct tmem_op op;
+	int rc = 0;
+
+	op.cmd = tmem_cmd;
+	op.pool_id = tmem_pool;
+	op.u.gen.oid[0] = oid.oid[0];
+	op.u.gen.oid[1] = oid.oid[1];
+	op.u.gen.oid[2] = oid.oid[2];
+	op.u.gen.index = index;
+	op.u.gen.tmem_offset = tmem_offset;
+	op.u.gen.pfn_offset = pfn_offset;
+	op.u.gen.len = len;
+	set_xen_guest_handle(op.u.gen.gmfn, (void *)gmfn);
+	rc = HYPERVISOR_tmem_op(&op);
+	return rc;
+}
+
+static int xen_tmem_new_pool(struct tmem_pool_uuid uuid,
+				u32 flags, unsigned long pagesize)
+{
+	struct tmem_op op;
+	int rc = 0, pageshift;
+
+	for (pageshift = 0; pagesize != 1; pageshift++)
+		pagesize >>= 1;
+	flags |= (pageshift - 12) << TMEM_POOL_PAGESIZE_SHIFT;
+	flags |= TMEM_SPEC_VERSION << TMEM_VERSION_SHIFT;
+	op.cmd = TMEM_NEW_POOL;
+	op.u.new.uuid[0] = uuid.uuid_lo;
+	op.u.new.uuid[1] = uuid.uuid_hi;
+	op.u.new.flags = flags;
+	rc = HYPERVISOR_tmem_op(&op);
+	return rc;
+}
+
+/* xen generic tmem ops */
+
+static int xen_tmem_put_page(u32 pool_id, struct tmem_oid oid,
+			     u32 index, unsigned long pfn)
+{
+	unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn;
+
+	return xen_tmem_op(TMEM_PUT_PAGE, pool_id, oid, index,
+		gmfn, 0, 0, 0);
+}
+
+static int xen_tmem_get_page(u32 pool_id, struct tmem_oid oid,
+			     u32 index, unsigned long pfn)
+{
+	unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn;
+
+	return xen_tmem_op(TMEM_GET_PAGE, pool_id, oid, index,
+		gmfn, 0, 0, 0);
+}
+
+static int xen_tmem_flush_page(u32 pool_id, struct tmem_oid oid, u32 index)
+{
+	return xen_tmem_op(TMEM_FLUSH_PAGE, pool_id, oid, index,
+		0, 0, 0, 0);
+}
+
+static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid)
+{
+	return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0);
+}
+
+bool __read_mostly tmem_enabled = false;
+
+static int __init enable_tmem(char *s)
+{
+	tmem_enabled = true;
+	return 1;
+}
+__setup("tmem", enable_tmem);
+
+#ifdef CONFIG_CLEANCACHE
+static int xen_tmem_destroy_pool(u32 pool_id)
+{
+	struct tmem_oid oid = { { 0 } };
+
+	return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
+}
+
+/* cleancache ops */
+
+static void tmem_cleancache_put_page(int pool, struct cleancache_filekey key,
+				     pgoff_t index, struct page *page)
+{
+	u32 ind = (u32) index;
+	struct tmem_oid oid = *(struct tmem_oid *)&key;
+	unsigned long pfn = page_to_pfn(page);
+
+	if (pool < 0)
+		return;
+	if (ind != index)
+		return;
+	mb(); /* ensure page is quiescent; tmem may address it with an alias */
+	(void)xen_tmem_put_page((u32)pool, oid, ind, pfn);
+}
+
+static int tmem_cleancache_get_page(int pool, struct cleancache_filekey key,
+				    pgoff_t index, struct page *page)
+{
+	u32 ind = (u32) index;
+	struct tmem_oid oid = *(struct tmem_oid *)&key;
+	unsigned long pfn = page_to_pfn(page);
+	int ret;
+
+	/* translate return values to linux semantics */
+	if (pool < 0)
+		return -1;
+	if (ind != index)
+		return -1;
+	ret = xen_tmem_get_page((u32)pool, oid, ind, pfn);
+	if (ret == 1)
+		return 0;
+	else
+		return -1;
+}
+
+static void tmem_cleancache_flush_page(int pool, struct cleancache_filekey key,
+				       pgoff_t index)
+{
+	u32 ind = (u32) index;
+	struct tmem_oid oid = *(struct tmem_oid *)&key;
+
+	if (pool < 0)
+		return;
+	if (ind != index)
+		return;
+	(void)xen_tmem_flush_page((u32)pool, oid, ind);
+}
+
+static void tmem_cleancache_flush_inode(int pool, struct cleancache_filekey key)
+{
+	struct tmem_oid oid = *(struct tmem_oid *)&key;
+
+	if (pool < 0)
+		return;
+	(void)xen_tmem_flush_object((u32)pool, oid);
+}
+
+static void tmem_cleancache_flush_fs(int pool)
+{
+	if (pool < 0)
+		return;
+	(void)xen_tmem_destroy_pool((u32)pool);
+}
+
+static int tmem_cleancache_init_fs(size_t pagesize)
+{
+	struct tmem_pool_uuid uuid_private = TMEM_POOL_PRIVATE_UUID;
+
+	return xen_tmem_new_pool(uuid_private, 0, pagesize);
+}
+
+static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize)
+{
+	struct tmem_pool_uuid shared_uuid;
+
+	shared_uuid.uuid_lo = *(u64 *)uuid;
+	shared_uuid.uuid_hi = *(u64 *)(&uuid[8]);
+	return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize);
+}
+
+static bool __initdata use_cleancache = true;
+
+static int __init no_cleancache(char *s)
+{
+	use_cleancache = false;
+	return 1;
+}
+__setup("nocleancache", no_cleancache);
+
+static struct cleancache_ops __initdata tmem_cleancache_ops = {
+	.put_page = tmem_cleancache_put_page,
+	.get_page = tmem_cleancache_get_page,
+	.invalidate_page = tmem_cleancache_flush_page,
+	.invalidate_inode = tmem_cleancache_flush_inode,
+	.invalidate_fs = tmem_cleancache_flush_fs,
+	.init_shared_fs = tmem_cleancache_init_shared_fs,
+	.init_fs = tmem_cleancache_init_fs
+};
+#endif
+
+#ifdef CONFIG_FRONTSWAP
+/* frontswap tmem operations */
+
+/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+static int tmem_frontswap_poolid;
+
+/*
+ * Swizzling increases objects per swaptype, increasing tmem concurrency
+ * for heavy swaploads.  Later, larger nr_cpus -> larger SWIZ_BITS
+ */
+#define SWIZ_BITS		4
+#define SWIZ_MASK		((1 << SWIZ_BITS) - 1)
+#define _oswiz(_type, _ind)	((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
+#define iswiz(_ind)		(_ind >> SWIZ_BITS)
+
+static inline struct tmem_oid oswiz(unsigned type, u32 ind)
+{
+	struct tmem_oid oid = { .oid = { 0 } };
+	oid.oid[0] = _oswiz(type, ind);
+	return oid;
+}
+
+/* returns 0 if the page was successfully put into frontswap, -1 if not */
+static int tmem_frontswap_put_page(unsigned type, pgoff_t offset,
+				   struct page *page)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	unsigned long pfn = page_to_pfn(page);
+	int pool = tmem_frontswap_poolid;
+	int ret;
+
+	if (pool < 0)
+		return -1;
+	if (ind64 != ind)
+		return -1;
+	mb(); /* ensure page is quiescent; tmem may address it with an alias */
+	ret = xen_tmem_put_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+	/* translate Xen tmem return values to linux semantics */
+	if (ret == 1)
+		return 0;
+	else
+		return -1;
+}
+
+/*
+ * returns 0 if the page was successfully gotten from frontswap, -1 if
+ * was not present (should never happen!)
+ */
+static int tmem_frontswap_get_page(unsigned type, pgoff_t offset,
+				   struct page *page)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	unsigned long pfn = page_to_pfn(page);
+	int pool = tmem_frontswap_poolid;
+	int ret;
+
+	if (pool < 0)
+		return -1;
+	if (ind64 != ind)
+		return -1;
+	ret = xen_tmem_get_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+	/* translate Xen tmem return values to linux semantics */
+	if (ret == 1)
+		return 0;
+	else
+		return -1;
+}
+
+/* flush a single page from frontswap */
+static void tmem_frontswap_flush_page(unsigned type, pgoff_t offset)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	int pool = tmem_frontswap_poolid;
+
+	if (pool < 0)
+		return;
+	if (ind64 != ind)
+		return;
+	(void) xen_tmem_flush_page(pool, oswiz(type, ind), iswiz(ind));
+}
+
+/* flush all pages from the passed swaptype */
+static void tmem_frontswap_flush_area(unsigned type)
+{
+	int pool = tmem_frontswap_poolid;
+	int ind;
+
+	if (pool < 0)
+		return;
+	for (ind = SWIZ_MASK; ind >= 0; ind--)
+		(void)xen_tmem_flush_object(pool, oswiz(type, ind));
+}
+
+static void tmem_frontswap_init(unsigned ignored)
+{
+	struct tmem_pool_uuid private = TMEM_POOL_PRIVATE_UUID;
+
+	/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+	if (tmem_frontswap_poolid < 0)
+		tmem_frontswap_poolid =
+		    xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE);
+}
+
+static bool __initdata use_frontswap = true;
+
+static int __init no_frontswap(char *s)
+{
+	use_frontswap = false;
+	return 1;
+}
+__setup("nofrontswap", no_frontswap);
+
+static struct frontswap_ops __initdata tmem_frontswap_ops = {
+	.put_page = tmem_frontswap_put_page,
+	.get_page = tmem_frontswap_get_page,
+	.invalidate_page = tmem_frontswap_flush_page,
+	.invalidate_area = tmem_frontswap_flush_area,
+	.init = tmem_frontswap_init
+};
+#endif
+
+static int __init xen_tmem_init(void)
+{
+	if (!xen_domain())
+		return 0;
+#ifdef CONFIG_FRONTSWAP
+	if (tmem_enabled && use_frontswap) {
+		char *s = "";
+		struct frontswap_ops old_ops =
+			frontswap_register_ops(&tmem_frontswap_ops);
+
+		tmem_frontswap_poolid = -1;
+		if (old_ops.init != NULL)
+			s = " (WARNING: frontswap_ops overridden)";
+		printk(KERN_INFO "frontswap enabled, RAM provided by "
+				 "Xen Transcendent Memory\n");
+	}
+#endif
+#ifdef CONFIG_CLEANCACHE
+	BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
+	if (tmem_enabled && use_cleancache) {
+		char *s = "";
+		struct cleancache_ops old_ops =
+			cleancache_register_ops(&tmem_cleancache_ops);
+		if (old_ops.init_fs != NULL)
+			s = " (WARNING: cleancache_ops overridden)";
+		printk(KERN_INFO "cleancache enabled, RAM provided by "
+				 "Xen Transcendent Memory%s\n", s);
+	}
+#endif
+	return 0;
+}
+
+module_init(xen_tmem_init)
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
new file mode 100644
index 00000000..0b48579a
--- /dev/null
+++ b/drivers/xen/xen-acpi-processor.c
@@ -0,0 +1,565 @@
+/*
+ * Copyright 2012 by Oracle Inc
+ * Author: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ *
+ * This code borrows ideas from https://lkml.org/lkml/2011/11/30/249
+ * so many thanks go to Kevin Tian <kevin.tian@intel.com>
+ * and Yu Ke <ke.yu@intel.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/cpumask.h>
+#include <linux/cpufreq.h>
+#include <linux/freezer.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/processor.h>
+
+#include <xen/interface/platform.h>
+#include <asm/xen/hypercall.h>
+
+#define DRV_NAME "xen-acpi-processor: "
+
+static int no_hypercall;
+MODULE_PARM_DESC(off, "Inhibit the hypercall.");
+module_param_named(off, no_hypercall, int, 0400);
+
+/*
+ * Note: Do not convert the acpi_id* below to cpumask_var_t or use cpumask_bit
+ * - as those shrink to nr_cpu_bits (which is dependent on possible_cpu), which
+ * can be less than what we want to put in. Instead use the 'nr_acpi_bits'
+ * which is dynamically computed based on the MADT or x2APIC table.
+ */
+static unsigned int nr_acpi_bits;
+/* Mutex to protect the acpi_ids_done - for CPU hotplug use. */
+static DEFINE_MUTEX(acpi_ids_mutex);
+/* Which ACPI ID we have processed from 'struct acpi_processor'. */
+static unsigned long *acpi_ids_done;
+/* Which ACPI ID exist in the SSDT/DSDT processor definitions. */
+static unsigned long __initdata *acpi_id_present;
+/* And if there is an _CST definition (or a PBLK) for the ACPI IDs */
+static unsigned long __initdata *acpi_id_cst_present;
+
+static int push_cxx_to_hypervisor(struct acpi_processor *_pr)
+{
+	struct xen_platform_op op = {
+		.cmd			= XENPF_set_processor_pminfo,
+		.interface_version	= XENPF_INTERFACE_VERSION,
+		.u.set_pminfo.id	= _pr->acpi_id,
+		.u.set_pminfo.type	= XEN_PM_CX,
+	};
+	struct xen_processor_cx *dst_cx, *dst_cx_states = NULL;
+	struct acpi_processor_cx *cx;
+	unsigned int i, ok;
+	int ret = 0;
+
+	dst_cx_states = kcalloc(_pr->power.count,
+				sizeof(struct xen_processor_cx), GFP_KERNEL);
+	if (!dst_cx_states)
+		return -ENOMEM;
+
+	for (ok = 0, i = 1; i <= _pr->power.count; i++) {
+		cx = &_pr->power.states[i];
+		if (!cx->valid)
+			continue;
+
+		dst_cx = &(dst_cx_states[ok++]);
+
+		dst_cx->reg.space_id = ACPI_ADR_SPACE_SYSTEM_IO;
+		if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
+			dst_cx->reg.bit_width = 8;
+			dst_cx->reg.bit_offset = 0;
+			dst_cx->reg.access_size = 1;
+		} else {
+			dst_cx->reg.space_id = ACPI_ADR_SPACE_FIXED_HARDWARE;
+			if (cx->entry_method == ACPI_CSTATE_FFH) {
+				/* NATIVE_CSTATE_BEYOND_HALT */
+				dst_cx->reg.bit_offset = 2;
+				dst_cx->reg.bit_width = 1; /* VENDOR_INTEL */
+			}
+			dst_cx->reg.access_size = 0;
+		}
+		dst_cx->reg.address = cx->address;
+
+		dst_cx->type = cx->type;
+		dst_cx->latency = cx->latency;
+		dst_cx->power = cx->power;
+
+		dst_cx->dpcnt = 0;
+		set_xen_guest_handle(dst_cx->dp, NULL);
+	}
+	if (!ok) {
+		pr_debug(DRV_NAME "No _Cx for ACPI CPU %u\n", _pr->acpi_id);
+		kfree(dst_cx_states);
+		return -EINVAL;
+	}
+	op.u.set_pminfo.power.count = ok;
+	op.u.set_pminfo.power.flags.bm_control = _pr->flags.bm_control;
+	op.u.set_pminfo.power.flags.bm_check = _pr->flags.bm_check;
+	op.u.set_pminfo.power.flags.has_cst = _pr->flags.has_cst;
+	op.u.set_pminfo.power.flags.power_setup_done =
+		_pr->flags.power_setup_done;
+
+	set_xen_guest_handle(op.u.set_pminfo.power.states, dst_cx_states);
+
+	if (!no_hypercall)
+		ret = HYPERVISOR_dom0_op(&op);
+
+	if (!ret) {
+		pr_debug("ACPI CPU%u - C-states uploaded.\n", _pr->acpi_id);
+		for (i = 1; i <= _pr->power.count; i++) {
+			cx = &_pr->power.states[i];
+			if (!cx->valid)
+				continue;
+			pr_debug("     C%d: %s %d uS\n",
+				 cx->type, cx->desc, (u32)cx->latency);
+		}
+	} else if (ret != -EINVAL)
+		/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
+		 * table is referencing a non-existing CPU - which can happen
+		 * with broken ACPI tables. */
+		pr_err(DRV_NAME "(CX): Hypervisor error (%d) for ACPI CPU%u\n",
+		       ret, _pr->acpi_id);
+
+	kfree(dst_cx_states);
+
+	return ret;
+}
+static struct xen_processor_px *
+xen_copy_pss_data(struct acpi_processor *_pr,
+		  struct xen_processor_performance *dst_perf)
+{
+	struct xen_processor_px *dst_states = NULL;
+	unsigned int i;
+
+	BUILD_BUG_ON(sizeof(struct xen_processor_px) !=
+		     sizeof(struct acpi_processor_px));
+
+	dst_states = kcalloc(_pr->performance->state_count,
+			     sizeof(struct xen_processor_px), GFP_KERNEL);
+	if (!dst_states)
+		return ERR_PTR(-ENOMEM);
+
+	dst_perf->state_count = _pr->performance->state_count;
+	for (i = 0; i < _pr->performance->state_count; i++) {
+		/* Fortunatly for us, they are both the same size */
+		memcpy(&(dst_states[i]), &(_pr->performance->states[i]),
+		       sizeof(struct acpi_processor_px));
+	}
+	return dst_states;
+}
+static int xen_copy_psd_data(struct acpi_processor *_pr,
+			     struct xen_processor_performance *dst)
+{
+	struct acpi_psd_package *pdomain;
+
+	BUILD_BUG_ON(sizeof(struct xen_psd_package) !=
+		     sizeof(struct acpi_psd_package));
+
+	/* This information is enumerated only if acpi_processor_preregister_performance
+	 * has been called.
+	 */
+	dst->shared_type = _pr->performance->shared_type;
+
+	pdomain = &(_pr->performance->domain_info);
+
+	/* 'acpi_processor_preregister_performance' does not parse if the
+	 * num_processors <= 1, but Xen still requires it. Do it manually here.
+	 */
+	if (pdomain->num_processors <= 1) {
+		if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
+			dst->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
+			dst->shared_type = CPUFREQ_SHARED_TYPE_HW;
+		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
+			dst->shared_type = CPUFREQ_SHARED_TYPE_ANY;
+
+	}
+	memcpy(&(dst->domain_info), pdomain, sizeof(struct acpi_psd_package));
+	return 0;
+}
+static int xen_copy_pct_data(struct acpi_pct_register *pct,
+			     struct xen_pct_register *dst_pct)
+{
+	/* It would be nice if you could just do 'memcpy(pct, dst_pct') but
+	 * sadly the Xen structure did not have the proper padding so the
+	 * descriptor field takes two (dst_pct) bytes instead of one (pct).
+	 */
+	dst_pct->descriptor = pct->descriptor;
+	dst_pct->length = pct->length;
+	dst_pct->space_id = pct->space_id;
+	dst_pct->bit_width = pct->bit_width;
+	dst_pct->bit_offset = pct->bit_offset;
+	dst_pct->reserved = pct->reserved;
+	dst_pct->address = pct->address;
+	return 0;
+}
+static int push_pxx_to_hypervisor(struct acpi_processor *_pr)
+{
+	int ret = 0;
+	struct xen_platform_op op = {
+		.cmd			= XENPF_set_processor_pminfo,
+		.interface_version	= XENPF_INTERFACE_VERSION,
+		.u.set_pminfo.id	= _pr->acpi_id,
+		.u.set_pminfo.type	= XEN_PM_PX,
+	};
+	struct xen_processor_performance *dst_perf;
+	struct xen_processor_px *dst_states = NULL;
+
+	dst_perf = &op.u.set_pminfo.perf;
+
+	dst_perf->platform_limit = _pr->performance_platform_limit;
+	dst_perf->flags |= XEN_PX_PPC;
+	xen_copy_pct_data(&(_pr->performance->control_register),
+			  &dst_perf->control_register);
+	xen_copy_pct_data(&(_pr->performance->status_register),
+			  &dst_perf->status_register);
+	dst_perf->flags |= XEN_PX_PCT;
+	dst_states = xen_copy_pss_data(_pr, dst_perf);
+	if (!IS_ERR_OR_NULL(dst_states)) {
+		set_xen_guest_handle(dst_perf->states, dst_states);
+		dst_perf->flags |= XEN_PX_PSS;
+	}
+	if (!xen_copy_psd_data(_pr, dst_perf))
+		dst_perf->flags |= XEN_PX_PSD;
+
+	if (dst_perf->flags != (XEN_PX_PSD | XEN_PX_PSS | XEN_PX_PCT | XEN_PX_PPC)) {
+		pr_warn(DRV_NAME "ACPI CPU%u missing some P-state data (%x), skipping.\n",
+			_pr->acpi_id, dst_perf->flags);
+		ret = -ENODEV;
+		goto err_free;
+	}
+
+	if (!no_hypercall)
+		ret = HYPERVISOR_dom0_op(&op);
+
+	if (!ret) {
+		struct acpi_processor_performance *perf;
+		unsigned int i;
+
+		perf = _pr->performance;
+		pr_debug("ACPI CPU%u - P-states uploaded.\n", _pr->acpi_id);
+		for (i = 0; i < perf->state_count; i++) {
+			pr_debug("     %cP%d: %d MHz, %d mW, %d uS\n",
+			(i == perf->state ? '*' : ' '), i,
+			(u32) perf->states[i].core_frequency,
+			(u32) perf->states[i].power,
+			(u32) perf->states[i].transition_latency);
+		}
+	} else if (ret != -EINVAL)
+		/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
+		 * table is referencing a non-existing CPU - which can happen
+		 * with broken ACPI tables. */
+		pr_warn(DRV_NAME "(_PXX): Hypervisor error (%d) for ACPI CPU%u\n",
+		       ret, _pr->acpi_id);
+err_free:
+	if (!IS_ERR_OR_NULL(dst_states))
+		kfree(dst_states);
+
+	return ret;
+}
+static int upload_pm_data(struct acpi_processor *_pr)
+{
+	int err = 0;
+
+	mutex_lock(&acpi_ids_mutex);
+	if (__test_and_set_bit(_pr->acpi_id, acpi_ids_done)) {
+		mutex_unlock(&acpi_ids_mutex);
+		return -EBUSY;
+	}
+	if (_pr->flags.power)
+		err = push_cxx_to_hypervisor(_pr);
+
+	if (_pr->performance && _pr->performance->states)
+		err |= push_pxx_to_hypervisor(_pr);
+
+	mutex_unlock(&acpi_ids_mutex);
+	return err;
+}
+static unsigned int __init get_max_acpi_id(void)
+{
+	struct xenpf_pcpuinfo *info;
+	struct xen_platform_op op = {
+		.cmd = XENPF_get_cpuinfo,
+		.interface_version = XENPF_INTERFACE_VERSION,
+	};
+	int ret = 0;
+	unsigned int i, last_cpu, max_acpi_id = 0;
+
+	info = &op.u.pcpu_info;
+	info->xen_cpuid = 0;
+
+	ret = HYPERVISOR_dom0_op(&op);
+	if (ret)
+		return NR_CPUS;
+
+	/* The max_present is the same irregardless of the xen_cpuid */
+	last_cpu = op.u.pcpu_info.max_present;
+	for (i = 0; i <= last_cpu; i++) {
+		info->xen_cpuid = i;
+		ret = HYPERVISOR_dom0_op(&op);
+		if (ret)
+			continue;
+		max_acpi_id = max(info->acpi_id, max_acpi_id);
+	}
+	max_acpi_id *= 2; /* Slack for CPU hotplug support. */
+	pr_debug(DRV_NAME "Max ACPI ID: %u\n", max_acpi_id);
+	return max_acpi_id;
+}
+/*
+ * The read_acpi_id and check_acpi_ids are there to support the Xen
+ * oddity of virtual CPUs != physical CPUs in the initial domain.
+ * The user can supply 'xen_max_vcpus=X' on the Xen hypervisor line
+ * which will band the amount of CPUs the initial domain can see.
+ * In general that is OK, except it plays havoc with any of the
+ * for_each_[present|online]_cpu macros which are banded to the virtual
+ * CPU amount.
+ */
+static acpi_status __init
+read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	u32 acpi_id;
+	acpi_status status;
+	acpi_object_type acpi_type;
+	unsigned long long tmp;
+	union acpi_object object = { 0 };
+	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
+	acpi_io_address pblk = 0;
+
+	status = acpi_get_type(handle, &acpi_type);
+	if (ACPI_FAILURE(status))
+		return AE_OK;
+
+	switch (acpi_type) {
+	case ACPI_TYPE_PROCESSOR:
+		status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+		if (ACPI_FAILURE(status))
+			return AE_OK;
+		acpi_id = object.processor.proc_id;
+		pblk = object.processor.pblk_address;
+		break;
+	case ACPI_TYPE_DEVICE:
+		status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp);
+		if (ACPI_FAILURE(status))
+			return AE_OK;
+		acpi_id = tmp;
+		break;
+	default:
+		return AE_OK;
+	}
+	/* There are more ACPI Processor objects than in x2APIC or MADT.
+	 * This can happen with incorrect ACPI SSDT declerations. */
+	if (acpi_id > nr_acpi_bits) {
+		pr_debug(DRV_NAME "We only have %u, trying to set %u\n",
+			 nr_acpi_bits, acpi_id);
+		return AE_OK;
+	}
+	/* OK, There is a ACPI Processor object */
+	__set_bit(acpi_id, acpi_id_present);
+
+	pr_debug(DRV_NAME "ACPI CPU%u w/ PBLK:0x%lx\n", acpi_id,
+		 (unsigned long)pblk);
+
+	status = acpi_evaluate_object(handle, "_CST", NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		if (!pblk)
+			return AE_OK;
+	}
+	/* .. and it has a C-state */
+	__set_bit(acpi_id, acpi_id_cst_present);
+
+	return AE_OK;
+}
+static int __init check_acpi_ids(struct acpi_processor *pr_backup)
+{
+
+	if (!pr_backup)
+		return -ENODEV;
+
+	/* All online CPUs have been processed at this stage. Now verify
+	 * whether in fact "online CPUs" == physical CPUs.
+	 */
+	acpi_id_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	if (!acpi_id_present)
+		return -ENOMEM;
+
+	acpi_id_cst_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	if (!acpi_id_cst_present) {
+		kfree(acpi_id_present);
+		return -ENOMEM;
+	}
+
+	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
+			    ACPI_UINT32_MAX,
+			    read_acpi_id, NULL, NULL, NULL);
+	acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL);
+
+	if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) {
+		unsigned int i;
+		for_each_set_bit(i, acpi_id_present, nr_acpi_bits) {
+			pr_backup->acpi_id = i;
+			/* Mask out C-states if there are no _CST or PBLK */
+			pr_backup->flags.power = test_bit(i, acpi_id_cst_present);
+			(void)upload_pm_data(pr_backup);
+		}
+	}
+	kfree(acpi_id_present);
+	acpi_id_present = NULL;
+	kfree(acpi_id_cst_present);
+	acpi_id_cst_present = NULL;
+	return 0;
+}
+static int __init check_prereq(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (!xen_initial_domain())
+		return -ENODEV;
+
+	if (!acpi_gbl_FADT.smi_command)
+		return -ENODEV;
+
+	if (c->x86_vendor == X86_VENDOR_INTEL) {
+		if (!cpu_has(c, X86_FEATURE_EST))
+			return -ENODEV;
+
+		return 0;
+	}
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
+		 * as we get compile warnings for the static functions.
+		 */
+#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
+#define USE_HW_PSTATE                   0x00000080
+		u32 eax, ebx, ecx, edx;
+		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
+		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
+			return -ENODEV;
+		return 0;
+	}
+	return -ENODEV;
+}
+/* acpi_perf_data is a pointer to percpu data. */
+static struct acpi_processor_performance __percpu *acpi_perf_data;
+
+static void free_acpi_perf_data(void)
+{
+	unsigned int i;
+
+	/* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
+	for_each_possible_cpu(i)
+		free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
+				 ->shared_cpu_map);
+	free_percpu(acpi_perf_data);
+}
+
+static int __init xen_acpi_processor_init(void)
+{
+	struct acpi_processor *pr_backup = NULL;
+	unsigned int i;
+	int rc = check_prereq();
+
+	if (rc)
+		return rc;
+
+	nr_acpi_bits = get_max_acpi_id() + 1;
+	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	if (!acpi_ids_done)
+		return -ENOMEM;
+
+	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
+	if (!acpi_perf_data) {
+		pr_debug(DRV_NAME "Memory allocation error for acpi_perf_data.\n");
+		kfree(acpi_ids_done);
+		return -ENOMEM;
+	}
+	for_each_possible_cpu(i) {
+		if (!zalloc_cpumask_var_node(
+			&per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
+			GFP_KERNEL, cpu_to_node(i))) {
+			rc = -ENOMEM;
+			goto err_out;
+		}
+	}
+
+	/* Do initialization in ACPI core. It is OK to fail here. */
+	(void)acpi_processor_preregister_performance(acpi_perf_data);
+
+	for_each_possible_cpu(i) {
+		struct acpi_processor_performance *perf;
+
+		perf = per_cpu_ptr(acpi_perf_data, i);
+		rc = acpi_processor_register_performance(perf, i);
+		if (rc)
+			goto err_out;
+	}
+	rc = acpi_processor_notify_smm(THIS_MODULE);
+	if (rc)
+		goto err_unregister;
+
+	for_each_possible_cpu(i) {
+		struct acpi_processor *_pr;
+		_pr = per_cpu(processors, i /* APIC ID */);
+		if (!_pr)
+			continue;
+
+		if (!pr_backup) {
+			pr_backup = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
+			memcpy(pr_backup, _pr, sizeof(struct acpi_processor));
+		}
+		(void)upload_pm_data(_pr);
+	}
+	rc = check_acpi_ids(pr_backup);
+	if (rc)
+		goto err_unregister;
+
+	kfree(pr_backup);
+
+	return 0;
+err_unregister:
+	for_each_possible_cpu(i) {
+		struct acpi_processor_performance *perf;
+		perf = per_cpu_ptr(acpi_perf_data, i);
+		acpi_processor_unregister_performance(perf, i);
+	}
+err_out:
+	/* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
+	free_acpi_perf_data();
+	kfree(acpi_ids_done);
+	return rc;
+}
+static void __exit xen_acpi_processor_exit(void)
+{
+	int i;
+
+	kfree(acpi_ids_done);
+	for_each_possible_cpu(i) {
+		struct acpi_processor_performance *perf;
+		perf = per_cpu_ptr(acpi_perf_data, i);
+		acpi_processor_unregister_performance(perf, i);
+	}
+	free_acpi_perf_data();
+}
+
+MODULE_AUTHOR("Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>");
+MODULE_DESCRIPTION("Xen ACPI Processor P-states (and Cx) driver which uploads PM data to Xen hypervisor");
+MODULE_LICENSE("GPL");
+
+/* We want to be loaded before the CPU freq scaling drivers are loaded.
+ * They are loaded in late_initcall. */
+device_initcall(xen_acpi_processor_init);
+module_exit(xen_acpi_processor_exit);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
new file mode 100644
index 00000000..8f37e23f
--- /dev/null
+++ b/drivers/xen/xen-balloon.c
@@ -0,0 +1,257 @@
+/******************************************************************************
+ * Xen balloon driver - enables returning/claiming memory to/from Xen.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/capability.h>
+
+#include <xen/xen.h>
+#include <xen/interface/xen.h>
+#include <xen/balloon.h>
+#include <xen/xenbus.h>
+#include <xen/features.h>
+#include <xen/page.h>
+
+#define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10))
+
+#define BALLOON_CLASS_NAME "xen_memory"
+
+static struct device balloon_dev;
+
+static int register_balloon(struct device *dev);
+
+/* React to a change in the target key */
+static void watch_target(struct xenbus_watch *watch,
+			 const char **vec, unsigned int len)
+{
+	unsigned long long new_target;
+	int err;
+
+	err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target);
+	if (err != 1) {
+		/* This is ok (for domain0 at least) - so just return */
+		return;
+	}
+
+	/* The given memory/target value is in KiB, so it needs converting to
+	 * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10.
+	 */
+	balloon_set_new_target(new_target >> (PAGE_SHIFT - 10));
+}
+static struct xenbus_watch target_watch = {
+	.node = "memory/target",
+	.callback = watch_target,
+};
+
+
+static int balloon_init_watcher(struct notifier_block *notifier,
+				unsigned long event,
+				void *data)
+{
+	int err;
+
+	err = register_xenbus_watch(&target_watch);
+	if (err)
+		printk(KERN_ERR "Failed to set balloon watcher\n");
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xenstore_notifier = {
+	.notifier_call = balloon_init_watcher,
+};
+
+static int __init balloon_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	pr_info("xen-balloon: Initialising balloon driver.\n");
+
+	register_balloon(&balloon_dev);
+
+	register_xen_selfballooning(&balloon_dev);
+
+	register_xenstore_notifier(&xenstore_notifier);
+
+	return 0;
+}
+subsys_initcall(balloon_init);
+
+static void balloon_exit(void)
+{
+    /* XXX - release balloon here */
+    return;
+}
+
+module_exit(balloon_exit);
+
+#define BALLOON_SHOW(name, format, args...)				\
+	static ssize_t show_##name(struct device *dev,			\
+				   struct device_attribute *attr,	\
+				   char *buf)				\
+	{								\
+		return sprintf(buf, format, ##args);			\
+	}								\
+	static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+
+BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages));
+BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low));
+BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high));
+
+static DEVICE_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay);
+static DEVICE_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay);
+static DEVICE_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count);
+static DEVICE_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count);
+
+static ssize_t show_target_kb(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	return sprintf(buf, "%lu\n", PAGES2KB(balloon_stats.target_pages));
+}
+
+static ssize_t store_target_kb(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	char *endchar;
+	unsigned long long target_bytes;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	target_bytes = simple_strtoull(buf, &endchar, 0) * 1024;
+
+	balloon_set_new_target(target_bytes >> PAGE_SHIFT);
+
+	return count;
+}
+
+static DEVICE_ATTR(target_kb, S_IRUGO | S_IWUSR,
+		   show_target_kb, store_target_kb);
+
+
+static ssize_t show_target(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	return sprintf(buf, "%llu\n",
+		       (unsigned long long)balloon_stats.target_pages
+		       << PAGE_SHIFT);
+}
+
+static ssize_t store_target(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf,
+			    size_t count)
+{
+	char *endchar;
+	unsigned long long target_bytes;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	target_bytes = memparse(buf, &endchar);
+
+	balloon_set_new_target(target_bytes >> PAGE_SHIFT);
+
+	return count;
+}
+
+static DEVICE_ATTR(target, S_IRUGO | S_IWUSR,
+		   show_target, store_target);
+
+
+static struct device_attribute *balloon_attrs[] = {
+	&dev_attr_target_kb,
+	&dev_attr_target,
+	&dev_attr_schedule_delay.attr,
+	&dev_attr_max_schedule_delay.attr,
+	&dev_attr_retry_count.attr,
+	&dev_attr_max_retry_count.attr
+};
+
+static struct attribute *balloon_info_attrs[] = {
+	&dev_attr_current_kb.attr,
+	&dev_attr_low_kb.attr,
+	&dev_attr_high_kb.attr,
+	NULL
+};
+
+static const struct attribute_group balloon_info_group = {
+	.name = "info",
+	.attrs = balloon_info_attrs
+};
+
+static struct bus_type balloon_subsys = {
+	.name = BALLOON_CLASS_NAME,
+	.dev_name = BALLOON_CLASS_NAME,
+};
+
+static int register_balloon(struct device *dev)
+{
+	int i, error;
+
+	error = subsys_system_register(&balloon_subsys, NULL);
+	if (error)
+		return error;
+
+	dev->id = 0;
+	dev->bus = &balloon_subsys;
+
+	error = device_register(dev);
+	if (error) {
+		bus_unregister(&balloon_subsys);
+		return error;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(balloon_attrs); i++) {
+		error = device_create_file(dev, balloon_attrs[i]);
+		if (error)
+			goto fail;
+	}
+
+	error = sysfs_create_group(&dev->kobj, &balloon_info_group);
+	if (error)
+		goto fail;
+
+	return 0;
+
+ fail:
+	while (--i >= 0)
+		device_remove_file(dev, balloon_attrs[i]);
+	device_unregister(dev);
+	bus_unregister(&balloon_subsys);
+	return error;
+}
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/xen-pciback/Makefile b/drivers/xen/xen-pciback/Makefile
new file mode 100644
index 00000000..ffe0ad34
--- /dev/null
+++ b/drivers/xen/xen-pciback/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback.o
+
+xen-pciback-y := pci_stub.o pciback_ops.o xenbus.o
+xen-pciback-y += conf_space.o conf_space_header.o \
+		 conf_space_capability.o \
+		 conf_space_quirks.o vpci.o \
+		 passthrough.o
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
new file mode 100644
index 00000000..30d7be02
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -0,0 +1,438 @@
+/*
+ * PCI Backend - Functions for creating a virtual configuration space for
+ *               exported PCI Devices.
+ *               It's dangerous to allow PCI Driver Domains to change their
+ *               device's resources (memory, i/o ports, interrupts). We need to
+ *               restrict changes to certain PCI Configuration registers:
+ *               BARs, INTERRUPT_PIN, most registers in the header...
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+#include "conf_space_quirks.h"
+
+static bool permissive;
+module_param(permissive, bool, 0644);
+
+/* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word,
+ * xen_pcibk_write_config_word, and xen_pcibk_write_config_byte are created. */
+#define DEFINE_PCI_CONFIG(op, size, type)			\
+int xen_pcibk_##op##_config_##size				\
+(struct pci_dev *dev, int offset, type value, void *data)	\
+{								\
+	return pci_##op##_config_##size(dev, offset, value);	\
+}
+
+DEFINE_PCI_CONFIG(read, byte, u8 *)
+DEFINE_PCI_CONFIG(read, word, u16 *)
+DEFINE_PCI_CONFIG(read, dword, u32 *)
+
+DEFINE_PCI_CONFIG(write, byte, u8)
+DEFINE_PCI_CONFIG(write, word, u16)
+DEFINE_PCI_CONFIG(write, dword, u32)
+
+static int conf_space_read(struct pci_dev *dev,
+			   const struct config_field_entry *entry,
+			   int offset, u32 *value)
+{
+	int ret = 0;
+	const struct config_field *field = entry->field;
+
+	*value = 0;
+
+	switch (field->size) {
+	case 1:
+		if (field->u.b.read)
+			ret = field->u.b.read(dev, offset, (u8 *) value,
+					      entry->data);
+		break;
+	case 2:
+		if (field->u.w.read)
+			ret = field->u.w.read(dev, offset, (u16 *) value,
+					      entry->data);
+		break;
+	case 4:
+		if (field->u.dw.read)
+			ret = field->u.dw.read(dev, offset, value, entry->data);
+		break;
+	}
+	return ret;
+}
+
+static int conf_space_write(struct pci_dev *dev,
+			    const struct config_field_entry *entry,
+			    int offset, u32 value)
+{
+	int ret = 0;
+	const struct config_field *field = entry->field;
+
+	switch (field->size) {
+	case 1:
+		if (field->u.b.write)
+			ret = field->u.b.write(dev, offset, (u8) value,
+					       entry->data);
+		break;
+	case 2:
+		if (field->u.w.write)
+			ret = field->u.w.write(dev, offset, (u16) value,
+					       entry->data);
+		break;
+	case 4:
+		if (field->u.dw.write)
+			ret = field->u.dw.write(dev, offset, value,
+						entry->data);
+		break;
+	}
+	return ret;
+}
+
+static inline u32 get_mask(int size)
+{
+	if (size == 1)
+		return 0xff;
+	else if (size == 2)
+		return 0xffff;
+	else
+		return 0xffffffff;
+}
+
+static inline int valid_request(int offset, int size)
+{
+	/* Validate request (no un-aligned requests) */
+	if ((size == 1 || size == 2 || size == 4) && (offset % size) == 0)
+		return 1;
+	return 0;
+}
+
+static inline u32 merge_value(u32 val, u32 new_val, u32 new_val_mask,
+			      int offset)
+{
+	if (offset >= 0) {
+		new_val_mask <<= (offset * 8);
+		new_val <<= (offset * 8);
+	} else {
+		new_val_mask >>= (offset * -8);
+		new_val >>= (offset * -8);
+	}
+	val = (val & ~new_val_mask) | (new_val & new_val_mask);
+
+	return val;
+}
+
+static int pcibios_err_to_errno(int err)
+{
+	switch (err) {
+	case PCIBIOS_SUCCESSFUL:
+		return XEN_PCI_ERR_success;
+	case PCIBIOS_DEVICE_NOT_FOUND:
+		return XEN_PCI_ERR_dev_not_found;
+	case PCIBIOS_BAD_REGISTER_NUMBER:
+		return XEN_PCI_ERR_invalid_offset;
+	case PCIBIOS_FUNC_NOT_SUPPORTED:
+		return XEN_PCI_ERR_not_implemented;
+	case PCIBIOS_SET_FAILED:
+		return XEN_PCI_ERR_access_denied;
+	}
+	return err;
+}
+
+int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
+			  u32 *ret_val)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+	int req_start, req_end, field_start, field_end;
+	/* if read fails for any reason, return 0
+	 * (as if device didn't respond) */
+	u32 value = 0, tmp_val;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: read %d bytes at 0x%x\n",
+		       pci_name(dev), size, offset);
+
+	if (!valid_request(offset, size)) {
+		err = XEN_PCI_ERR_invalid_offset;
+		goto out;
+	}
+
+	/* Get the real value first, then modify as appropriate */
+	switch (size) {
+	case 1:
+		err = pci_read_config_byte(dev, offset, (u8 *) &value);
+		break;
+	case 2:
+		err = pci_read_config_word(dev, offset, (u16 *) &value);
+		break;
+	case 4:
+		err = pci_read_config_dword(dev, offset, &value);
+		break;
+	}
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		req_start = offset;
+		req_end = offset + size;
+		field_start = OFFSET(cfg_entry);
+		field_end = OFFSET(cfg_entry) + field->size;
+
+		if ((req_start >= field_start && req_start < field_end)
+		    || (req_end > field_start && req_end <= field_end)) {
+			err = conf_space_read(dev, cfg_entry, field_start,
+					      &tmp_val);
+			if (err)
+				goto out;
+
+			value = merge_value(value, tmp_val,
+					    get_mask(field->size),
+					    field_start - req_start);
+		}
+	}
+
+out:
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: read %d bytes at 0x%x = %x\n",
+		       pci_name(dev), size, offset, value);
+
+	*ret_val = value;
+	return pcibios_err_to_errno(err);
+}
+
+int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
+{
+	int err = 0, handled = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+	u32 tmp_val;
+	int req_start, req_end, field_start, field_end;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG
+		       DRV_NAME ": %s: write request %d bytes at 0x%x = %x\n",
+		       pci_name(dev), size, offset, value);
+
+	if (!valid_request(offset, size))
+		return XEN_PCI_ERR_invalid_offset;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		req_start = offset;
+		req_end = offset + size;
+		field_start = OFFSET(cfg_entry);
+		field_end = OFFSET(cfg_entry) + field->size;
+
+		if ((req_start >= field_start && req_start < field_end)
+		    || (req_end > field_start && req_end <= field_end)) {
+			tmp_val = 0;
+
+			err = xen_pcibk_config_read(dev, field_start,
+						  field->size, &tmp_val);
+			if (err)
+				break;
+
+			tmp_val = merge_value(tmp_val, value, get_mask(size),
+					      req_start - field_start);
+
+			err = conf_space_write(dev, cfg_entry, field_start,
+					       tmp_val);
+
+			/* handled is set true here, but not every byte
+			 * may have been written! Properly detecting if
+			 * every byte is handled is unnecessary as the
+			 * flag is used to detect devices that need
+			 * special helpers to work correctly.
+			 */
+			handled = 1;
+		}
+	}
+
+	if (!handled && !err) {
+		/* By default, anything not specificially handled above is
+		 * read-only. The permissive flag changes this behavior so
+		 * that anything not specifically handled above is writable.
+		 * This means that some fields may still be read-only because
+		 * they have entries in the config_field list that intercept
+		 * the write and do nothing. */
+		if (dev_data->permissive || permissive) {
+			switch (size) {
+			case 1:
+				err = pci_write_config_byte(dev, offset,
+							    (u8) value);
+				break;
+			case 2:
+				err = pci_write_config_word(dev, offset,
+							    (u16) value);
+				break;
+			case 4:
+				err = pci_write_config_dword(dev, offset,
+							     (u32) value);
+				break;
+			}
+		} else if (!dev_data->warned_on_write) {
+			dev_data->warned_on_write = 1;
+			dev_warn(&dev->dev, "Driver tried to write to a "
+				 "read-only configuration space field at offset"
+				 " 0x%x, size %d. This may be harmless, but if "
+				 "you have problems with your device:\n"
+				 "1) see permissive attribute in sysfs\n"
+				 "2) report problems to the xen-devel "
+				 "mailing list along with details of your "
+				 "device obtained from lspci.\n", offset, size);
+		}
+	}
+
+	return pcibios_err_to_errno(err);
+}
+
+void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry, *t;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "free-ing dynamically allocated virtual "
+			   "configuration space fields\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry_safe(cfg_entry, t, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		if (field->clean) {
+			field->clean((struct config_field *)field);
+
+			kfree(cfg_entry->data);
+
+			list_del(&cfg_entry->list);
+			kfree(cfg_entry);
+		}
+
+	}
+}
+
+void xen_pcibk_config_reset_dev(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "resetting virtual configuration space\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		if (field->reset)
+			field->reset(dev, OFFSET(cfg_entry), cfg_entry->data);
+	}
+}
+
+void xen_pcibk_config_free_dev(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry, *t;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "free-ing virtual configuration space fields\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry_safe(cfg_entry, t, &dev_data->config_fields, list) {
+		list_del(&cfg_entry->list);
+
+		field = cfg_entry->field;
+
+		if (field->release)
+			field->release(dev, OFFSET(cfg_entry), cfg_entry->data);
+
+		kfree(cfg_entry);
+	}
+}
+
+int xen_pcibk_config_add_field_offset(struct pci_dev *dev,
+				    const struct config_field *field,
+				    unsigned int base_offset)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry;
+	void *tmp;
+
+	cfg_entry = kmalloc(sizeof(*cfg_entry), GFP_KERNEL);
+	if (!cfg_entry) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	cfg_entry->data = NULL;
+	cfg_entry->field = field;
+	cfg_entry->base_offset = base_offset;
+
+	/* silently ignore duplicate fields */
+	err = xen_pcibk_field_is_dup(dev, OFFSET(cfg_entry));
+	if (err)
+		goto out;
+
+	if (field->init) {
+		tmp = field->init(dev, OFFSET(cfg_entry));
+
+		if (IS_ERR(tmp)) {
+			err = PTR_ERR(tmp);
+			goto out;
+		}
+
+		cfg_entry->data = tmp;
+	}
+
+	dev_dbg(&dev->dev, "added config field at offset 0x%02x\n",
+		OFFSET(cfg_entry));
+	list_add_tail(&cfg_entry->list, &dev_data->config_fields);
+
+out:
+	if (err)
+		kfree(cfg_entry);
+
+	return err;
+}
+
+/* This sets up the device's virtual configuration space to keep track of
+ * certain registers (like the base address registers (BARs) so that we can
+ * keep the client from manipulating them directly.
+ */
+int xen_pcibk_config_init_dev(struct pci_dev *dev)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+
+	dev_dbg(&dev->dev, "initializing virtual configuration space\n");
+
+	INIT_LIST_HEAD(&dev_data->config_fields);
+
+	err = xen_pcibk_config_header_add_fields(dev);
+	if (err)
+		goto out;
+
+	err = xen_pcibk_config_capability_add_fields(dev);
+	if (err)
+		goto out;
+
+	err = xen_pcibk_config_quirks_init(dev);
+
+out:
+	return err;
+}
+
+int xen_pcibk_config_init(void)
+{
+	return xen_pcibk_config_capability_init();
+}
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
new file mode 100644
index 00000000..e56c934a
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -0,0 +1,126 @@
+/*
+ * PCI Backend - Common data structures for overriding the configuration space
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#ifndef __XEN_PCIBACK_CONF_SPACE_H__
+#define __XEN_PCIBACK_CONF_SPACE_H__
+
+#include <linux/list.h>
+#include <linux/err.h>
+
+/* conf_field_init can return an errno in a ptr with ERR_PTR() */
+typedef void *(*conf_field_init) (struct pci_dev *dev, int offset);
+typedef void (*conf_field_reset) (struct pci_dev *dev, int offset, void *data);
+typedef void (*conf_field_free) (struct pci_dev *dev, int offset, void *data);
+
+typedef int (*conf_dword_write) (struct pci_dev *dev, int offset, u32 value,
+				 void *data);
+typedef int (*conf_word_write) (struct pci_dev *dev, int offset, u16 value,
+				void *data);
+typedef int (*conf_byte_write) (struct pci_dev *dev, int offset, u8 value,
+				void *data);
+typedef int (*conf_dword_read) (struct pci_dev *dev, int offset, u32 *value,
+				void *data);
+typedef int (*conf_word_read) (struct pci_dev *dev, int offset, u16 *value,
+			       void *data);
+typedef int (*conf_byte_read) (struct pci_dev *dev, int offset, u8 *value,
+			       void *data);
+
+/* These are the fields within the configuration space which we
+ * are interested in intercepting reads/writes to and changing their
+ * values.
+ */
+struct config_field {
+	unsigned int offset;
+	unsigned int size;
+	unsigned int mask;
+	conf_field_init init;
+	conf_field_reset reset;
+	conf_field_free release;
+	void (*clean) (struct config_field *field);
+	union {
+		struct {
+			conf_dword_write write;
+			conf_dword_read read;
+		} dw;
+		struct {
+			conf_word_write write;
+			conf_word_read read;
+		} w;
+		struct {
+			conf_byte_write write;
+			conf_byte_read read;
+		} b;
+	} u;
+	struct list_head list;
+};
+
+struct config_field_entry {
+	struct list_head list;
+	const struct config_field *field;
+	unsigned int base_offset;
+	void *data;
+};
+
+#define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
+
+/* Add fields to a device - the add_fields macro expects to get a pointer to
+ * the first entry in an array (of which the ending is marked by size==0)
+ */
+int xen_pcibk_config_add_field_offset(struct pci_dev *dev,
+				    const struct config_field *field,
+				    unsigned int offset);
+
+static inline int xen_pcibk_config_add_field(struct pci_dev *dev,
+					   const struct config_field *field)
+{
+	return xen_pcibk_config_add_field_offset(dev, field, 0);
+}
+
+static inline int xen_pcibk_config_add_fields(struct pci_dev *dev,
+					    const struct config_field *field)
+{
+	int i, err = 0;
+	for (i = 0; field[i].size != 0; i++) {
+		err = xen_pcibk_config_add_field(dev, &field[i]);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static inline int xen_pcibk_config_add_fields_offset(struct pci_dev *dev,
+					const struct config_field *field,
+					unsigned int offset)
+{
+	int i, err = 0;
+	for (i = 0; field[i].size != 0; i++) {
+		err = xen_pcibk_config_add_field_offset(dev, &field[i], offset);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+/* Read/Write the real configuration space */
+int xen_pcibk_read_config_byte(struct pci_dev *dev, int offset, u8 *value,
+			       void *data);
+int xen_pcibk_read_config_word(struct pci_dev *dev, int offset, u16 *value,
+			       void *data);
+int xen_pcibk_read_config_dword(struct pci_dev *dev, int offset, u32 *value,
+				void *data);
+int xen_pcibk_write_config_byte(struct pci_dev *dev, int offset, u8 value,
+				 void *data);
+int xen_pcibk_write_config_word(struct pci_dev *dev, int offset, u16 value,
+				void *data);
+int xen_pcibk_write_config_dword(struct pci_dev *dev, int offset, u32 value,
+				 void *data);
+
+int xen_pcibk_config_capability_init(void);
+
+int xen_pcibk_config_header_add_fields(struct pci_dev *dev);
+int xen_pcibk_config_capability_add_fields(struct pci_dev *dev);
+
+#endif				/* __XEN_PCIBACK_CONF_SPACE_H__ */
diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c
new file mode 100644
index 00000000..7f83e908
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space_capability.c
@@ -0,0 +1,207 @@
+/*
+ * PCI Backend - Handles the virtual fields found on the capability lists
+ *               in the configuration space.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+
+static LIST_HEAD(capabilities);
+struct xen_pcibk_config_capability {
+	struct list_head cap_list;
+
+	int capability;
+
+	/* If the device has the capability found above, add these fields */
+	const struct config_field *fields;
+};
+
+static const struct config_field caplist_header[] = {
+	{
+	 .offset    = PCI_CAP_LIST_ID,
+	 .size      = 2, /* encompass PCI_CAP_LIST_ID & PCI_CAP_LIST_NEXT */
+	 .u.w.read  = xen_pcibk_read_config_word,
+	 .u.w.write = NULL,
+	},
+	{}
+};
+
+static inline void register_capability(struct xen_pcibk_config_capability *cap)
+{
+	list_add_tail(&cap->cap_list, &capabilities);
+}
+
+int xen_pcibk_config_capability_add_fields(struct pci_dev *dev)
+{
+	int err = 0;
+	struct xen_pcibk_config_capability *cap;
+	int cap_offset;
+
+	list_for_each_entry(cap, &capabilities, cap_list) {
+		cap_offset = pci_find_capability(dev, cap->capability);
+		if (cap_offset) {
+			dev_dbg(&dev->dev, "Found capability 0x%x at 0x%x\n",
+				cap->capability, cap_offset);
+
+			err = xen_pcibk_config_add_fields_offset(dev,
+							       caplist_header,
+							       cap_offset);
+			if (err)
+				goto out;
+			err = xen_pcibk_config_add_fields_offset(dev,
+							       cap->fields,
+							       cap_offset);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	return err;
+}
+
+static int vpd_address_write(struct pci_dev *dev, int offset, u16 value,
+			     void *data)
+{
+	/* Disallow writes to the vital product data */
+	if (value & PCI_VPD_ADDR_F)
+		return PCIBIOS_SET_FAILED;
+	else
+		return pci_write_config_word(dev, offset, value);
+}
+
+static const struct config_field caplist_vpd[] = {
+	{
+	 .offset    = PCI_VPD_ADDR,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_config_word,
+	 .u.w.write = vpd_address_write,
+	 },
+	{
+	 .offset     = PCI_VPD_DATA,
+	 .size       = 4,
+	 .u.dw.read  = xen_pcibk_read_config_dword,
+	 .u.dw.write = NULL,
+	 },
+	{}
+};
+
+static int pm_caps_read(struct pci_dev *dev, int offset, u16 *value,
+			void *data)
+{
+	int err;
+	u16 real_value;
+
+	err = pci_read_config_word(dev, offset, &real_value);
+	if (err)
+		goto out;
+
+	*value = real_value & ~PCI_PM_CAP_PME_MASK;
+
+out:
+	return err;
+}
+
+/* PM_OK_BITS specifies the bits that the driver domain is allowed to change.
+ * Can't allow driver domain to enable PMEs - they're shared */
+#define PM_OK_BITS (PCI_PM_CTRL_PME_STATUS|PCI_PM_CTRL_DATA_SEL_MASK)
+
+static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value,
+			 void *data)
+{
+	int err;
+	u16 old_value;
+	pci_power_t new_state, old_state;
+
+	err = pci_read_config_word(dev, offset, &old_value);
+	if (err)
+		goto out;
+
+	old_state = (pci_power_t)(old_value & PCI_PM_CTRL_STATE_MASK);
+	new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
+
+	new_value &= PM_OK_BITS;
+	if ((old_value & PM_OK_BITS) != new_value) {
+		new_value = (old_value & ~PM_OK_BITS) | new_value;
+		err = pci_write_config_word(dev, offset, new_value);
+		if (err)
+			goto out;
+	}
+
+	/* Let pci core handle the power management change */
+	dev_dbg(&dev->dev, "set power state to %x\n", new_state);
+	err = pci_set_power_state(dev, new_state);
+	if (err) {
+		err = PCIBIOS_SET_FAILED;
+		goto out;
+	}
+
+ out:
+	return err;
+}
+
+/* Ensure PMEs are disabled */
+static void *pm_ctrl_init(struct pci_dev *dev, int offset)
+{
+	int err;
+	u16 value;
+
+	err = pci_read_config_word(dev, offset, &value);
+	if (err)
+		goto out;
+
+	if (value & PCI_PM_CTRL_PME_ENABLE) {
+		value &= ~PCI_PM_CTRL_PME_ENABLE;
+		err = pci_write_config_word(dev, offset, value);
+	}
+
+out:
+	return ERR_PTR(err);
+}
+
+static const struct config_field caplist_pm[] = {
+	{
+		.offset     = PCI_PM_PMC,
+		.size       = 2,
+		.u.w.read   = pm_caps_read,
+	},
+	{
+		.offset     = PCI_PM_CTRL,
+		.size       = 2,
+		.init       = pm_ctrl_init,
+		.u.w.read   = xen_pcibk_read_config_word,
+		.u.w.write  = pm_ctrl_write,
+	},
+	{
+		.offset     = PCI_PM_PPB_EXTENSIONS,
+		.size       = 1,
+		.u.b.read   = xen_pcibk_read_config_byte,
+	},
+	{
+		.offset     = PCI_PM_DATA_REGISTER,
+		.size       = 1,
+		.u.b.read   = xen_pcibk_read_config_byte,
+	},
+	{}
+};
+
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_pm = {
+	.capability = PCI_CAP_ID_PM,
+	.fields = caplist_pm,
+};
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_vpd = {
+	.capability = PCI_CAP_ID_VPD,
+	.fields = caplist_vpd,
+};
+
+int xen_pcibk_config_capability_init(void)
+{
+	register_capability(&xen_pcibk_config_capability_vpd);
+	register_capability(&xen_pcibk_config_capability_pm);
+
+	return 0;
+}
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
new file mode 100644
index 00000000..3daf862d
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -0,0 +1,385 @@
+/*
+ * PCI Backend - Handles the virtual fields in the configuration space headers.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+
+struct pci_bar_info {
+	u32 val;
+	u32 len_val;
+	int which;
+};
+
+#define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO))
+#define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER)
+
+static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+{
+	int i;
+	int ret;
+
+	ret = xen_pcibk_read_config_word(dev, offset, value, data);
+	if (!pci_is_enabled(dev))
+		return ret;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		if (dev->resource[i].flags & IORESOURCE_IO)
+			*value |= PCI_COMMAND_IO;
+		if (dev->resource[i].flags & IORESOURCE_MEM)
+			*value |= PCI_COMMAND_MEMORY;
+	}
+
+	return ret;
+}
+
+static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int err;
+
+	dev_data = pci_get_drvdata(dev);
+	if (!pci_is_enabled(dev) && is_enable_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: enable\n",
+			       pci_name(dev));
+		err = pci_enable_device(dev);
+		if (err)
+			return err;
+		if (dev_data)
+			dev_data->enable_intx = 1;
+	} else if (pci_is_enabled(dev) && !is_enable_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: disable\n",
+			       pci_name(dev));
+		pci_disable_device(dev);
+		if (dev_data)
+			dev_data->enable_intx = 0;
+	}
+
+	if (!dev->is_busmaster && is_master_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: set bus master\n",
+			       pci_name(dev));
+		pci_set_master(dev);
+	}
+
+	if (value & PCI_COMMAND_INVALIDATE) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG
+			       DRV_NAME ": %s: enable memory-write-invalidate\n",
+			       pci_name(dev));
+		err = pci_set_mwi(dev);
+		if (err) {
+			printk(KERN_WARNING
+			       DRV_NAME ": %s: cannot enable "
+			       "memory-write-invalidate (%d)\n",
+			       pci_name(dev), err);
+			value &= ~PCI_COMMAND_INVALIDATE;
+		}
+	}
+
+	return pci_write_config_word(dev, offset, value);
+}
+
+static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* A write to obtain the length must happen as a 32-bit write.
+	 * This does not (yet) support writing individual bytes
+	 */
+	if (value == ~PCI_ROM_ADDRESS_ENABLE)
+		bar->which = 1;
+	else {
+		u32 tmpval;
+		pci_read_config_dword(dev, offset, &tmpval);
+		if (tmpval != bar->val && value == bar->val) {
+			/* Allow restoration of bar value. */
+			pci_write_config_dword(dev, offset, bar->val);
+		}
+		bar->which = 0;
+	}
+
+	/* Do we need to support enabling/disabling the rom address here? */
+
+	return 0;
+}
+
+/* For the BARs, only allow writes which write ~0 or
+ * the correct resource information
+ * (Needed for when the driver probes the resource usage)
+ */
+static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* A write to obtain the length must happen as a 32-bit write.
+	 * This does not (yet) support writing individual bytes
+	 */
+	if (value == ~0)
+		bar->which = 1;
+	else {
+		u32 tmpval;
+		pci_read_config_dword(dev, offset, &tmpval);
+		if (tmpval != bar->val && value == bar->val) {
+			/* Allow restoration of bar value. */
+			pci_write_config_dword(dev, offset, bar->val);
+		}
+		bar->which = 0;
+	}
+
+	return 0;
+}
+
+static int bar_read(struct pci_dev *dev, int offset, u32 * value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	*value = bar->which ? bar->len_val : bar->val;
+
+	return 0;
+}
+
+static inline void read_dev_bar(struct pci_dev *dev,
+				struct pci_bar_info *bar_info, int offset,
+				u32 len_mask)
+{
+	int	pos;
+	struct resource	*res = dev->resource;
+
+	if (offset == PCI_ROM_ADDRESS || offset == PCI_ROM_ADDRESS1)
+		pos = PCI_ROM_RESOURCE;
+	else {
+		pos = (offset - PCI_BASE_ADDRESS_0) / 4;
+		if (pos && ((res[pos - 1].flags & (PCI_BASE_ADDRESS_SPACE |
+				PCI_BASE_ADDRESS_MEM_TYPE_MASK)) ==
+			   (PCI_BASE_ADDRESS_SPACE_MEMORY |
+				PCI_BASE_ADDRESS_MEM_TYPE_64))) {
+			bar_info->val = res[pos - 1].start >> 32;
+			bar_info->len_val = res[pos - 1].end >> 32;
+			return;
+		}
+	}
+
+	bar_info->val = res[pos].start |
+			(res[pos].flags & PCI_REGION_FLAG_MASK);
+	bar_info->len_val = resource_size(&res[pos]);
+}
+
+static void *bar_init(struct pci_dev *dev, int offset)
+{
+	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+
+	if (!bar)
+		return ERR_PTR(-ENOMEM);
+
+	read_dev_bar(dev, bar, offset, ~0);
+	bar->which = 0;
+
+	return bar;
+}
+
+static void *rom_init(struct pci_dev *dev, int offset)
+{
+	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+
+	if (!bar)
+		return ERR_PTR(-ENOMEM);
+
+	read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE);
+	bar->which = 0;
+
+	return bar;
+}
+
+static void bar_reset(struct pci_dev *dev, int offset, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	bar->which = 0;
+}
+
+static void bar_release(struct pci_dev *dev, int offset, void *data)
+{
+	kfree(data);
+}
+
+static int xen_pcibk_read_vendor(struct pci_dev *dev, int offset,
+			       u16 *value, void *data)
+{
+	*value = dev->vendor;
+
+	return 0;
+}
+
+static int xen_pcibk_read_device(struct pci_dev *dev, int offset,
+			       u16 *value, void *data)
+{
+	*value = dev->device;
+
+	return 0;
+}
+
+static int interrupt_read(struct pci_dev *dev, int offset, u8 * value,
+			  void *data)
+{
+	*value = (u8) dev->irq;
+
+	return 0;
+}
+
+static int bist_write(struct pci_dev *dev, int offset, u8 value, void *data)
+{
+	u8 cur_value;
+	int err;
+
+	err = pci_read_config_byte(dev, offset, &cur_value);
+	if (err)
+		goto out;
+
+	if ((cur_value & ~PCI_BIST_START) == (value & ~PCI_BIST_START)
+	    || value == PCI_BIST_START)
+		err = pci_write_config_byte(dev, offset, value);
+
+out:
+	return err;
+}
+
+static const struct config_field header_common[] = {
+	{
+	 .offset    = PCI_VENDOR_ID,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_vendor,
+	},
+	{
+	 .offset    = PCI_DEVICE_ID,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_device,
+	},
+	{
+	 .offset    = PCI_COMMAND,
+	 .size      = 2,
+	 .u.w.read  = command_read,
+	 .u.w.write = command_write,
+	},
+	{
+	 .offset    = PCI_INTERRUPT_LINE,
+	 .size      = 1,
+	 .u.b.read  = interrupt_read,
+	},
+	{
+	 .offset    = PCI_INTERRUPT_PIN,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	},
+	{
+	 /* Any side effects of letting driver domain control cache line? */
+	 .offset    = PCI_CACHE_LINE_SIZE,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	 .u.b.write = xen_pcibk_write_config_byte,
+	},
+	{
+	 .offset    = PCI_LATENCY_TIMER,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	},
+	{
+	 .offset    = PCI_BIST,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	 .u.b.write = bist_write,
+	},
+	{}
+};
+
+#define CFG_FIELD_BAR(reg_offset)			\
+	{						\
+	.offset     = reg_offset,			\
+	.size       = 4,				\
+	.init       = bar_init,				\
+	.reset      = bar_reset,			\
+	.release    = bar_release,			\
+	.u.dw.read  = bar_read,				\
+	.u.dw.write = bar_write,			\
+	}
+
+#define CFG_FIELD_ROM(reg_offset)			\
+	{						\
+	.offset     = reg_offset,			\
+	.size       = 4,				\
+	.init       = rom_init,				\
+	.reset      = bar_reset,			\
+	.release    = bar_release,			\
+	.u.dw.read  = bar_read,				\
+	.u.dw.write = rom_write,			\
+	}
+
+static const struct config_field header_0[] = {
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_0),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_1),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_2),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_3),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_4),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_5),
+	CFG_FIELD_ROM(PCI_ROM_ADDRESS),
+	{}
+};
+
+static const struct config_field header_1[] = {
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_0),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_1),
+	CFG_FIELD_ROM(PCI_ROM_ADDRESS1),
+	{}
+};
+
+int xen_pcibk_config_header_add_fields(struct pci_dev *dev)
+{
+	int err;
+
+	err = xen_pcibk_config_add_fields(dev, header_common);
+	if (err)
+		goto out;
+
+	switch (dev->hdr_type) {
+	case PCI_HEADER_TYPE_NORMAL:
+		err = xen_pcibk_config_add_fields(dev, header_0);
+		break;
+
+	case PCI_HEADER_TYPE_BRIDGE:
+		err = xen_pcibk_config_add_fields(dev, header_1);
+		break;
+
+	default:
+		err = -EINVAL;
+		printk(KERN_ERR DRV_NAME ": %s: Unsupported header type %d!\n",
+		       pci_name(dev), dev->hdr_type);
+		break;
+	}
+
+out:
+	return err;
+}
diff --git a/drivers/xen/xen-pciback/conf_space_quirks.c b/drivers/xen/xen-pciback/conf_space_quirks.c
new file mode 100644
index 00000000..7476791c
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space_quirks.c
@@ -0,0 +1,139 @@
+/*
+ * PCI Backend - Handle special overlays for broken devices.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Author: Chris Bookholt <hap10@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+#include "conf_space_quirks.h"
+
+LIST_HEAD(xen_pcibk_quirks);
+static inline const struct pci_device_id *
+match_one_device(const struct pci_device_id *id, const struct pci_dev *dev)
+{
+	if ((id->vendor == PCI_ANY_ID || id->vendor == dev->vendor) &&
+	    (id->device == PCI_ANY_ID || id->device == dev->device) &&
+	    (id->subvendor == PCI_ANY_ID ||
+				id->subvendor == dev->subsystem_vendor) &&
+	    (id->subdevice == PCI_ANY_ID ||
+				id->subdevice == dev->subsystem_device) &&
+	    !((id->class ^ dev->class) & id->class_mask))
+		return id;
+	return NULL;
+}
+
+static struct xen_pcibk_config_quirk *xen_pcibk_find_quirk(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *tmp_quirk;
+
+	list_for_each_entry(tmp_quirk, &xen_pcibk_quirks, quirks_list)
+		if (match_one_device(&tmp_quirk->devid, dev) != NULL)
+			goto out;
+	tmp_quirk = NULL;
+	printk(KERN_DEBUG DRV_NAME
+	       ": quirk didn't match any device known\n");
+out:
+	return tmp_quirk;
+}
+
+static inline void register_quirk(struct xen_pcibk_config_quirk *quirk)
+{
+	list_add_tail(&quirk->quirks_list, &xen_pcibk_quirks);
+}
+
+int xen_pcibk_field_is_dup(struct pci_dev *dev, unsigned int reg)
+{
+	int ret = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		if (OFFSET(cfg_entry) == reg) {
+			ret = 1;
+			break;
+		}
+	}
+	return ret;
+}
+
+int xen_pcibk_config_quirks_add_field(struct pci_dev *dev, struct config_field
+				    *field)
+{
+	int err = 0;
+
+	switch (field->size) {
+	case 1:
+		field->u.b.read = xen_pcibk_read_config_byte;
+		field->u.b.write = xen_pcibk_write_config_byte;
+		break;
+	case 2:
+		field->u.w.read = xen_pcibk_read_config_word;
+		field->u.w.write = xen_pcibk_write_config_word;
+		break;
+	case 4:
+		field->u.dw.read = xen_pcibk_read_config_dword;
+		field->u.dw.write = xen_pcibk_write_config_dword;
+		break;
+	default:
+		err = -EINVAL;
+		goto out;
+	}
+
+	xen_pcibk_config_add_field(dev, field);
+
+out:
+	return err;
+}
+
+int xen_pcibk_config_quirks_init(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *quirk;
+	int ret = 0;
+
+	quirk = kzalloc(sizeof(*quirk), GFP_ATOMIC);
+	if (!quirk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	quirk->devid.vendor = dev->vendor;
+	quirk->devid.device = dev->device;
+	quirk->devid.subvendor = dev->subsystem_vendor;
+	quirk->devid.subdevice = dev->subsystem_device;
+	quirk->devid.class = 0;
+	quirk->devid.class_mask = 0;
+	quirk->devid.driver_data = 0UL;
+
+	quirk->pdev = dev;
+
+	register_quirk(quirk);
+out:
+	return ret;
+}
+
+void xen_pcibk_config_field_free(struct config_field *field)
+{
+	kfree(field);
+}
+
+int xen_pcibk_config_quirk_release(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *quirk;
+	int ret = 0;
+
+	quirk = xen_pcibk_find_quirk(dev);
+	if (!quirk) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+	list_del(&quirk->quirks_list);
+	kfree(quirk);
+
+out:
+	return ret;
+}
diff --git a/drivers/xen/xen-pciback/conf_space_quirks.h b/drivers/xen/xen-pciback/conf_space_quirks.h
new file mode 100644
index 00000000..cfcc517e
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space_quirks.h
@@ -0,0 +1,33 @@
+/*
+ * PCI Backend - Data structures for special overlays for broken devices.
+ *
+ * Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Chris Bookholt <hap10@epoch.ncsc.mil>
+ */
+
+#ifndef __XEN_PCIBACK_CONF_SPACE_QUIRKS_H__
+#define __XEN_PCIBACK_CONF_SPACE_QUIRKS_H__
+
+#include <linux/pci.h>
+#include <linux/list.h>
+
+struct xen_pcibk_config_quirk {
+	struct list_head quirks_list;
+	struct pci_device_id devid;
+	struct pci_dev *pdev;
+};
+
+int xen_pcibk_config_quirks_add_field(struct pci_dev *dev, struct config_field
+				    *field);
+
+int xen_pcibk_config_quirks_remove_field(struct pci_dev *dev, int reg);
+
+int xen_pcibk_config_quirks_init(struct pci_dev *dev);
+
+void xen_pcibk_config_field_free(struct config_field *field);
+
+int xen_pcibk_config_quirk_release(struct pci_dev *dev);
+
+int xen_pcibk_field_is_dup(struct pci_dev *dev, unsigned int reg);
+
+#endif
diff --git a/drivers/xen/xen-pciback/passthrough.c b/drivers/xen/xen-pciback/passthrough.c
new file mode 100644
index 00000000..828dddc3
--- /dev/null
+++ b/drivers/xen/xen-pciback/passthrough.c
@@ -0,0 +1,188 @@
+/*
+ * PCI Backend - Provides restricted access to the real PCI bus topology
+ *               to the frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/mutex.h>
+#include "pciback.h"
+
+struct passthrough_dev_data {
+	/* Access to dev_list must be protected by lock */
+	struct list_head dev_list;
+	struct mutex lock;
+};
+
+static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
+					       unsigned int domain,
+					       unsigned int bus,
+					       unsigned int devfn)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry;
+	struct pci_dev *dev = NULL;
+
+	mutex_lock(&dev_data->lock);
+
+	list_for_each_entry(dev_entry, &dev_data->dev_list, list) {
+		if (domain == (unsigned int)pci_domain_nr(dev_entry->dev->bus)
+		    && bus == (unsigned int)dev_entry->dev->bus->number
+		    && devfn == dev_entry->dev->devfn) {
+			dev = dev_entry->dev;
+			break;
+		}
+	}
+
+	mutex_unlock(&dev_data->lock);
+
+	return dev;
+}
+
+static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
+				   struct pci_dev *dev,
+				   int devid, publish_pci_dev_cb publish_cb)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry;
+	unsigned int domain, bus, devfn;
+	int err;
+
+	dev_entry = kmalloc(sizeof(*dev_entry), GFP_KERNEL);
+	if (!dev_entry)
+		return -ENOMEM;
+	dev_entry->dev = dev;
+
+	mutex_lock(&dev_data->lock);
+	list_add_tail(&dev_entry->list, &dev_data->dev_list);
+	mutex_unlock(&dev_data->lock);
+
+	/* Publish this device. */
+	domain = (unsigned int)pci_domain_nr(dev->bus);
+	bus = (unsigned int)dev->bus->number;
+	devfn = dev->devfn;
+	err = publish_cb(pdev, domain, bus, devfn, devid);
+
+	return err;
+}
+
+static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *t;
+	struct pci_dev *found_dev = NULL;
+
+	mutex_lock(&dev_data->lock);
+
+	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		if (dev_entry->dev == dev) {
+			list_del(&dev_entry->list);
+			found_dev = dev_entry->dev;
+			kfree(dev_entry);
+		}
+	}
+
+	mutex_unlock(&dev_data->lock);
+
+	if (found_dev)
+		pcistub_put_pci_dev(found_dev);
+}
+
+static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+{
+	struct passthrough_dev_data *dev_data;
+
+	dev_data = kmalloc(sizeof(*dev_data), GFP_KERNEL);
+	if (!dev_data)
+		return -ENOMEM;
+
+	mutex_init(&dev_data->lock);
+
+	INIT_LIST_HEAD(&dev_data->dev_list);
+
+	pdev->pci_dev_data = dev_data;
+
+	return 0;
+}
+
+static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					 publish_pci_root_cb publish_root_cb)
+{
+	int err = 0;
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *e;
+	struct pci_dev *dev;
+	int found;
+	unsigned int domain, bus;
+
+	mutex_lock(&dev_data->lock);
+
+	list_for_each_entry(dev_entry, &dev_data->dev_list, list) {
+		/* Only publish this device as a root if none of its
+		 * parent bridges are exported
+		 */
+		found = 0;
+		dev = dev_entry->dev->bus->self;
+		for (; !found && dev != NULL; dev = dev->bus->self) {
+			list_for_each_entry(e, &dev_data->dev_list, list) {
+				if (dev == e->dev) {
+					found = 1;
+					break;
+				}
+			}
+		}
+
+		domain = (unsigned int)pci_domain_nr(dev_entry->dev->bus);
+		bus = (unsigned int)dev_entry->dev->bus->number;
+
+		if (!found) {
+			err = publish_root_cb(pdev, domain, bus);
+			if (err)
+				break;
+		}
+	}
+
+	mutex_unlock(&dev_data->lock);
+
+	return err;
+}
+
+static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *t;
+
+	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		list_del(&dev_entry->list);
+		pcistub_put_pci_dev(dev_entry->dev);
+		kfree(dev_entry);
+	}
+
+	kfree(dev_data);
+	pdev->pci_dev_data = NULL;
+}
+
+static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					struct xen_pcibk_device *pdev,
+					unsigned int *domain, unsigned int *bus,
+					unsigned int *devfn)
+{
+	*domain = pci_domain_nr(pcidev->bus);
+	*bus = pcidev->bus->number;
+	*devfn = pcidev->devfn;
+	return 1;
+}
+
+const struct xen_pcibk_backend xen_pcibk_passthrough_backend = {
+	.name           = "passthrough",
+	.init           = __xen_pcibk_init_devices,
+	.free		= __xen_pcibk_release_devices,
+	.find           = __xen_pcibk_get_pcifront_dev,
+	.publish        = __xen_pcibk_publish_pci_roots,
+	.release        = __xen_pcibk_release_pci_dev,
+	.add            = __xen_pcibk_add_pci_dev,
+	.get            = __xen_pcibk_get_pci_dev,
+};
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
new file mode 100644
index 00000000..097e536e
--- /dev/null
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -0,0 +1,1410 @@
+/*
+ * PCI Stub Driver - Grabs devices in backend to be exported later
+ *
+ * Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Chris Bookholt <hap10@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rwsem.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/kref.h>
+#include <linux/pci.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <xen/events.h>
+#include <asm/xen/pci.h>
+#include <asm/xen/hypervisor.h>
+#include "pciback.h"
+#include "conf_space.h"
+#include "conf_space_quirks.h"
+
+static char *pci_devs_to_hide;
+wait_queue_head_t xen_pcibk_aer_wait_queue;
+/*Add sem for sync AER handling and xen_pcibk remove/reconfigue ops,
+* We want to avoid in middle of AER ops, xen_pcibk devices is being removed
+*/
+static DECLARE_RWSEM(pcistub_sem);
+module_param_named(hide, pci_devs_to_hide, charp, 0444);
+
+struct pcistub_device_id {
+	struct list_head slot_list;
+	int domain;
+	unsigned char bus;
+	unsigned int devfn;
+};
+static LIST_HEAD(pcistub_device_ids);
+static DEFINE_SPINLOCK(device_ids_lock);
+
+struct pcistub_device {
+	struct kref kref;
+	struct list_head dev_list;
+	spinlock_t lock;
+
+	struct pci_dev *dev;
+	struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
+};
+
+/* Access to pcistub_devices & seized_devices lists and the initialize_devices
+ * flag must be locked with pcistub_devices_lock
+ */
+static DEFINE_SPINLOCK(pcistub_devices_lock);
+static LIST_HEAD(pcistub_devices);
+
+/* wait for device_initcall before initializing our devices
+ * (see pcistub_init_devices_late)
+ */
+static int initialize_devices;
+static LIST_HEAD(seized_devices);
+
+static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+
+	dev_dbg(&dev->dev, "pcistub_device_alloc\n");
+
+	psdev = kzalloc(sizeof(*psdev), GFP_ATOMIC);
+	if (!psdev)
+		return NULL;
+
+	psdev->dev = pci_dev_get(dev);
+	if (!psdev->dev) {
+		kfree(psdev);
+		return NULL;
+	}
+
+	kref_init(&psdev->kref);
+	spin_lock_init(&psdev->lock);
+
+	return psdev;
+}
+
+/* Don't call this directly as it's called by pcistub_device_put */
+static void pcistub_device_release(struct kref *kref)
+{
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+
+	psdev = container_of(kref, struct pcistub_device, kref);
+	dev_data = pci_get_drvdata(psdev->dev);
+
+	dev_dbg(&psdev->dev->dev, "pcistub_device_release\n");
+
+	xen_unregister_device_domain_owner(psdev->dev);
+
+	/* Call the reset function which does not take lock as this
+	 * is called from "unbind" which takes a device_lock mutex.
+	 */
+	__pci_reset_function_locked(psdev->dev);
+	if (pci_load_and_free_saved_state(psdev->dev,
+					  &dev_data->pci_saved_state)) {
+		dev_dbg(&psdev->dev->dev, "Could not reload PCI state\n");
+	} else
+		pci_restore_state(psdev->dev);
+
+	/* Disable the device */
+	xen_pcibk_reset_device(psdev->dev);
+
+	kfree(dev_data);
+	pci_set_drvdata(psdev->dev, NULL);
+
+	/* Clean-up the device */
+	xen_pcibk_config_free_dyn_fields(psdev->dev);
+	xen_pcibk_config_free_dev(psdev->dev);
+
+	psdev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+	pci_dev_put(psdev->dev);
+
+	kfree(psdev);
+}
+
+static inline void pcistub_device_get(struct pcistub_device *psdev)
+{
+	kref_get(&psdev->kref);
+}
+
+static inline void pcistub_device_put(struct pcistub_device *psdev)
+{
+	kref_put(&psdev->kref, pcistub_device_release);
+}
+
+static struct pcistub_device *pcistub_device_find(int domain, int bus,
+						  int slot, int func)
+{
+	struct pcistub_device *psdev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (psdev->dev != NULL
+		    && domain == pci_domain_nr(psdev->dev->bus)
+		    && bus == psdev->dev->bus->number
+		    && PCI_DEVFN(slot, func) == psdev->dev->devfn) {
+			pcistub_device_get(psdev);
+			goto out;
+		}
+	}
+
+	/* didn't find it */
+	psdev = NULL;
+
+out:
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return psdev;
+}
+
+static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
+						  struct pcistub_device *psdev)
+{
+	struct pci_dev *pci_dev = NULL;
+	unsigned long flags;
+
+	pcistub_device_get(psdev);
+
+	spin_lock_irqsave(&psdev->lock, flags);
+	if (!psdev->pdev) {
+		psdev->pdev = pdev;
+		pci_dev = psdev->dev;
+	}
+	spin_unlock_irqrestore(&psdev->lock, flags);
+
+	if (!pci_dev)
+		pcistub_device_put(psdev);
+
+	return pci_dev;
+}
+
+struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
+					    int domain, int bus,
+					    int slot, int func)
+{
+	struct pcistub_device *psdev;
+	struct pci_dev *found_dev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (psdev->dev != NULL
+		    && domain == pci_domain_nr(psdev->dev->bus)
+		    && bus == psdev->dev->bus->number
+		    && PCI_DEVFN(slot, func) == psdev->dev->devfn) {
+			found_dev = pcistub_device_get_pci_dev(pdev, psdev);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return found_dev;
+}
+
+struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
+				    struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+	struct pci_dev *found_dev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (psdev->dev == dev) {
+			found_dev = pcistub_device_get_pci_dev(pdev, psdev);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return found_dev;
+}
+
+void pcistub_put_pci_dev(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev, *found_psdev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (psdev->dev == dev) {
+			found_psdev = psdev;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	if (WARN_ON(!found_psdev))
+		return;
+
+	/*hold this lock for avoiding breaking link between
+	* pcistub and xen_pcibk when AER is in processing
+	*/
+	down_write(&pcistub_sem);
+	/* Cleanup our device
+	 * (so it's ready for the next domain)
+	 */
+
+	/* This is OK - we are running from workqueue context
+	 * and want to inhibit the user from fiddling with 'reset'
+	 */
+	pci_reset_function(dev);
+	pci_restore_state(psdev->dev);
+
+	/* This disables the device. */
+	xen_pcibk_reset_device(found_psdev->dev);
+
+	/* And cleanup up our emulated fields. */
+	xen_pcibk_config_free_dyn_fields(found_psdev->dev);
+	xen_pcibk_config_reset_dev(found_psdev->dev);
+
+	xen_unregister_device_domain_owner(found_psdev->dev);
+
+	spin_lock_irqsave(&found_psdev->lock, flags);
+	found_psdev->pdev = NULL;
+	spin_unlock_irqrestore(&found_psdev->lock, flags);
+
+	pcistub_device_put(found_psdev);
+	up_write(&pcistub_sem);
+}
+
+static int __devinit pcistub_match_one(struct pci_dev *dev,
+				       struct pcistub_device_id *pdev_id)
+{
+	/* Match the specified device by domain, bus, slot, func and also if
+	 * any of the device's parent bridges match.
+	 */
+	for (; dev != NULL; dev = dev->bus->self) {
+		if (pci_domain_nr(dev->bus) == pdev_id->domain
+		    && dev->bus->number == pdev_id->bus
+		    && dev->devfn == pdev_id->devfn)
+			return 1;
+
+		/* Sometimes topmost bridge links to itself. */
+		if (dev == dev->bus->self)
+			break;
+	}
+
+	return 0;
+}
+
+static int __devinit pcistub_match(struct pci_dev *dev)
+{
+	struct pcistub_device_id *pdev_id;
+	unsigned long flags;
+	int found = 0;
+
+	spin_lock_irqsave(&device_ids_lock, flags);
+	list_for_each_entry(pdev_id, &pcistub_device_ids, slot_list) {
+		if (pcistub_match_one(dev, pdev_id)) {
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&device_ids_lock, flags);
+
+	return found;
+}
+
+static int __devinit pcistub_init_device(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int err = 0;
+
+	dev_dbg(&dev->dev, "initializing...\n");
+
+	/* The PCI backend is not intended to be a module (or to work with
+	 * removable PCI devices (yet). If it were, xen_pcibk_config_free()
+	 * would need to be called somewhere to free the memory allocated
+	 * here and then to call kfree(pci_get_drvdata(psdev->dev)).
+	 */
+	dev_data = kzalloc(sizeof(*dev_data) +  strlen(DRV_NAME "[]")
+				+ strlen(pci_name(dev)) + 1, GFP_ATOMIC);
+	if (!dev_data) {
+		err = -ENOMEM;
+		goto out;
+	}
+	pci_set_drvdata(dev, dev_data);
+
+	/*
+	 * Setup name for fake IRQ handler. It will only be enabled
+	 * once the device is turned on by the guest.
+	 */
+	sprintf(dev_data->irq_name, DRV_NAME "[%s]", pci_name(dev));
+
+	dev_dbg(&dev->dev, "initializing config\n");
+
+	init_waitqueue_head(&xen_pcibk_aer_wait_queue);
+	err = xen_pcibk_config_init_dev(dev);
+	if (err)
+		goto out;
+
+	/* HACK: Force device (& ACPI) to determine what IRQ it's on - we
+	 * must do this here because pcibios_enable_device may specify
+	 * the pci device's true irq (and possibly its other resources)
+	 * if they differ from what's in the configuration space.
+	 * This makes the assumption that the device's resources won't
+	 * change after this point (otherwise this code may break!)
+	 */
+	dev_dbg(&dev->dev, "enabling device\n");
+	err = pci_enable_device(dev);
+	if (err)
+		goto config_release;
+
+	dev_dbg(&dev->dev, "reseting (FLR, D3, etc) the device\n");
+	__pci_reset_function_locked(dev);
+
+	/* We need the device active to save the state. */
+	dev_dbg(&dev->dev, "save state of device\n");
+	pci_save_state(dev);
+	dev_data->pci_saved_state = pci_store_saved_state(dev);
+	if (!dev_data->pci_saved_state)
+		dev_err(&dev->dev, "Could not store PCI conf saved state!\n");
+
+	/* Now disable the device (this also ensures some private device
+	 * data is setup before we export)
+	 */
+	dev_dbg(&dev->dev, "reset device\n");
+	xen_pcibk_reset_device(dev);
+
+	dev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+	return 0;
+
+config_release:
+	xen_pcibk_config_free_dev(dev);
+
+out:
+	pci_set_drvdata(dev, NULL);
+	kfree(dev_data);
+	return err;
+}
+
+/*
+ * Because some initialization still happens on
+ * devices during fs_initcall, we need to defer
+ * full initialization of our devices until
+ * device_initcall.
+ */
+static int __init pcistub_init_devices_late(void)
+{
+	struct pcistub_device *psdev;
+	unsigned long flags;
+	int err = 0;
+
+	pr_debug(DRV_NAME ": pcistub_init_devices_late\n");
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	while (!list_empty(&seized_devices)) {
+		psdev = container_of(seized_devices.next,
+				     struct pcistub_device, dev_list);
+		list_del(&psdev->dev_list);
+
+		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+		err = pcistub_init_device(psdev->dev);
+		if (err) {
+			dev_err(&psdev->dev->dev,
+				"error %d initializing device\n", err);
+			kfree(psdev);
+			psdev = NULL;
+		}
+
+		spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+		if (psdev)
+			list_add_tail(&psdev->dev_list, &pcistub_devices);
+	}
+
+	initialize_devices = 1;
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+	return 0;
+}
+
+static int __devinit pcistub_seize(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+	unsigned long flags;
+	int err = 0;
+
+	psdev = pcistub_device_alloc(dev);
+	if (!psdev)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	if (initialize_devices) {
+		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+		/* don't want irqs disabled when calling pcistub_init_device */
+		err = pcistub_init_device(psdev->dev);
+
+		spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+		if (!err)
+			list_add(&psdev->dev_list, &pcistub_devices);
+	} else {
+		dev_dbg(&dev->dev, "deferring initialization\n");
+		list_add(&psdev->dev_list, &seized_devices);
+	}
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+	if (err)
+		pcistub_device_put(psdev);
+
+	return err;
+}
+
+static int __devinit pcistub_probe(struct pci_dev *dev,
+				   const struct pci_device_id *id)
+{
+	int err = 0;
+
+	dev_dbg(&dev->dev, "probing...\n");
+
+	if (pcistub_match(dev)) {
+
+		if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL
+		    && dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+			dev_err(&dev->dev, "can't export pci devices that "
+				"don't have a normal (0) or bridge (1) "
+				"header type!\n");
+			err = -ENODEV;
+			goto out;
+		}
+
+		dev_info(&dev->dev, "seizing device\n");
+		err = pcistub_seize(dev);
+	} else
+		/* Didn't find the device */
+		err = -ENODEV;
+
+out:
+	return err;
+}
+
+static void pcistub_remove(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev, *found_psdev = NULL;
+	unsigned long flags;
+
+	dev_dbg(&dev->dev, "removing\n");
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+
+	xen_pcibk_config_quirk_release(dev);
+
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (psdev->dev == dev) {
+			found_psdev = psdev;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+	if (found_psdev) {
+		dev_dbg(&dev->dev, "found device to remove - in use? %p\n",
+			found_psdev->pdev);
+
+		if (found_psdev->pdev) {
+			printk(KERN_WARNING DRV_NAME ": ****** removing device "
+			       "%s while still in-use! ******\n",
+			       pci_name(found_psdev->dev));
+			printk(KERN_WARNING DRV_NAME ": ****** driver domain may"
+			       " still access this device's i/o resources!\n");
+			printk(KERN_WARNING DRV_NAME ": ****** shutdown driver "
+			       "domain before binding device\n");
+			printk(KERN_WARNING DRV_NAME ": ****** to other drivers "
+			       "or domains\n");
+
+			xen_pcibk_release_pci_dev(found_psdev->pdev,
+						found_psdev->dev);
+		}
+
+		spin_lock_irqsave(&pcistub_devices_lock, flags);
+		list_del(&found_psdev->dev_list);
+		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+
+		/* the final put for releasing from the list */
+		pcistub_device_put(found_psdev);
+	}
+}
+
+static DEFINE_PCI_DEVICE_TABLE(pcistub_ids) = {
+	{
+	 .vendor = PCI_ANY_ID,
+	 .device = PCI_ANY_ID,
+	 .subvendor = PCI_ANY_ID,
+	 .subdevice = PCI_ANY_ID,
+	 },
+	{0,},
+};
+
+#define PCI_NODENAME_MAX 40
+static void kill_domain_by_device(struct pcistub_device *psdev)
+{
+	struct xenbus_transaction xbt;
+	int err;
+	char nodename[PCI_NODENAME_MAX];
+
+	BUG_ON(!psdev);
+	snprintf(nodename, PCI_NODENAME_MAX, "/local/domain/0/backend/pci/%d/0",
+		psdev->pdev->xdev->otherend_id);
+
+again:
+	err = xenbus_transaction_start(&xbt);
+	if (err) {
+		dev_err(&psdev->dev->dev,
+			"error %d when start xenbus transaction\n", err);
+		return;
+	}
+	/*PV AER handlers will set this flag*/
+	xenbus_printf(xbt, nodename, "aerState" , "aerfail");
+	err = xenbus_transaction_end(xbt, 0);
+	if (err) {
+		if (err == -EAGAIN)
+			goto again;
+		dev_err(&psdev->dev->dev,
+			"error %d when end xenbus transaction\n", err);
+		return;
+	}
+}
+
+/* For each aer recovery step error_detected, mmio_enabled, etc, front_end and
+ * backend need to have cooperation. In xen_pcibk, those steps will do similar
+ * jobs: send service request and waiting for front_end response.
+*/
+static pci_ers_result_t common_process(struct pcistub_device *psdev,
+				       pci_channel_state_t state, int aer_cmd,
+				       pci_ers_result_t result)
+{
+	pci_ers_result_t res = result;
+	struct xen_pcie_aer_op *aer_op;
+	int ret;
+
+	/*with PV AER drivers*/
+	aer_op = &(psdev->pdev->sh_info->aer_op);
+	aer_op->cmd = aer_cmd ;
+	/*useful for error_detected callback*/
+	aer_op->err = state;
+	/*pcifront_end BDF*/
+	ret = xen_pcibk_get_pcifront_dev(psdev->dev, psdev->pdev,
+		&aer_op->domain, &aer_op->bus, &aer_op->devfn);
+	if (!ret) {
+		dev_err(&psdev->dev->dev,
+			DRV_NAME ": failed to get pcifront device\n");
+		return PCI_ERS_RESULT_NONE;
+	}
+	wmb();
+
+	dev_dbg(&psdev->dev->dev,
+			DRV_NAME ": aer_op %x dom %x bus %x devfn %x\n",
+			aer_cmd, aer_op->domain, aer_op->bus, aer_op->devfn);
+	/*local flag to mark there's aer request, xen_pcibk callback will use
+	* this flag to judge whether we need to check pci-front give aer
+	* service ack signal
+	*/
+	set_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+
+	/*It is possible that a pcifront conf_read_write ops request invokes
+	* the callback which cause the spurious execution of wake_up.
+	* Yet it is harmless and better than a spinlock here
+	*/
+	set_bit(_XEN_PCIB_active,
+		(unsigned long *)&psdev->pdev->sh_info->flags);
+	wmb();
+	notify_remote_via_irq(psdev->pdev->evtchn_irq);
+
+	ret = wait_event_timeout(xen_pcibk_aer_wait_queue,
+				 !(test_bit(_XEN_PCIB_active, (unsigned long *)
+				 &psdev->pdev->sh_info->flags)), 300*HZ);
+
+	if (!ret) {
+		if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&psdev->pdev->sh_info->flags)) {
+			dev_err(&psdev->dev->dev,
+				"pcifront aer process not responding!\n");
+			clear_bit(_XEN_PCIB_active,
+			  (unsigned long *)&psdev->pdev->sh_info->flags);
+			aer_op->err = PCI_ERS_RESULT_NONE;
+			return res;
+		}
+	}
+	clear_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+
+	if (test_bit(_XEN_PCIF_active,
+		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		dev_dbg(&psdev->dev->dev,
+			"schedule pci_conf service in " DRV_NAME "\n");
+		xen_pcibk_test_and_schedule_op(psdev->pdev);
+	}
+
+	res = (pci_ers_result_t)aer_op->err;
+	return res;
+}
+
+/*
+* xen_pcibk_slot_reset: it will send the slot_reset request to  pcifront in case
+* of the device driver could provide this service, and then wait for pcifront
+* ack.
+* @dev: pointer to PCI devices
+* return value is used by aer_core do_recovery policy
+*/
+static pci_ers_result_t xen_pcibk_slot_reset(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+	pci_ers_result_t result;
+
+	result = PCI_ERS_RESULT_RECOVERED;
+	dev_dbg(&dev->dev, "xen_pcibk_slot_reset(bus:%x,devfn:%x)\n",
+		dev->bus->number, dev->devfn);
+
+	down_write(&pcistub_sem);
+	psdev = pcistub_device_find(pci_domain_nr(dev->bus),
+				dev->bus->number,
+				PCI_SLOT(dev->devfn),
+				PCI_FUNC(dev->devfn));
+
+	if (!psdev || !psdev->pdev) {
+		dev_err(&dev->dev,
+			DRV_NAME " device is not found/assigned\n");
+		goto end;
+	}
+
+	if (!psdev->pdev->sh_info) {
+		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
+			" by HVM, kill it\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+
+	if (!test_bit(_XEN_PCIB_AERHANDLER,
+		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		dev_err(&dev->dev,
+			"guest with no AER driver should have been killed\n");
+		goto release;
+	}
+	result = common_process(psdev, 1, XEN_PCI_OP_aer_slotreset, result);
+
+	if (result == PCI_ERS_RESULT_NONE ||
+		result == PCI_ERS_RESULT_DISCONNECT) {
+		dev_dbg(&dev->dev,
+			"No AER slot_reset service or disconnected!\n");
+		kill_domain_by_device(psdev);
+	}
+release:
+	pcistub_device_put(psdev);
+end:
+	up_write(&pcistub_sem);
+	return result;
+
+}
+
+
+/*xen_pcibk_mmio_enabled: it will send the mmio_enabled request to  pcifront
+* in case of the device driver could provide this service, and then wait
+* for pcifront ack
+* @dev: pointer to PCI devices
+* return value is used by aer_core do_recovery policy
+*/
+
+static pci_ers_result_t xen_pcibk_mmio_enabled(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+	pci_ers_result_t result;
+
+	result = PCI_ERS_RESULT_RECOVERED;
+	dev_dbg(&dev->dev, "xen_pcibk_mmio_enabled(bus:%x,devfn:%x)\n",
+		dev->bus->number, dev->devfn);
+
+	down_write(&pcistub_sem);
+	psdev = pcistub_device_find(pci_domain_nr(dev->bus),
+				dev->bus->number,
+				PCI_SLOT(dev->devfn),
+				PCI_FUNC(dev->devfn));
+
+	if (!psdev || !psdev->pdev) {
+		dev_err(&dev->dev,
+			DRV_NAME " device is not found/assigned\n");
+		goto end;
+	}
+
+	if (!psdev->pdev->sh_info) {
+		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
+			" by HVM, kill it\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+
+	if (!test_bit(_XEN_PCIB_AERHANDLER,
+		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		dev_err(&dev->dev,
+			"guest with no AER driver should have been killed\n");
+		goto release;
+	}
+	result = common_process(psdev, 1, XEN_PCI_OP_aer_mmio, result);
+
+	if (result == PCI_ERS_RESULT_NONE ||
+		result == PCI_ERS_RESULT_DISCONNECT) {
+		dev_dbg(&dev->dev,
+			"No AER mmio_enabled service or disconnected!\n");
+		kill_domain_by_device(psdev);
+	}
+release:
+	pcistub_device_put(psdev);
+end:
+	up_write(&pcistub_sem);
+	return result;
+}
+
+/*xen_pcibk_error_detected: it will send the error_detected request to  pcifront
+* in case of the device driver could provide this service, and then wait
+* for pcifront ack.
+* @dev: pointer to PCI devices
+* @error: the current PCI connection state
+* return value is used by aer_core do_recovery policy
+*/
+
+static pci_ers_result_t xen_pcibk_error_detected(struct pci_dev *dev,
+	pci_channel_state_t error)
+{
+	struct pcistub_device *psdev;
+	pci_ers_result_t result;
+
+	result = PCI_ERS_RESULT_CAN_RECOVER;
+	dev_dbg(&dev->dev, "xen_pcibk_error_detected(bus:%x,devfn:%x)\n",
+		dev->bus->number, dev->devfn);
+
+	down_write(&pcistub_sem);
+	psdev = pcistub_device_find(pci_domain_nr(dev->bus),
+				dev->bus->number,
+				PCI_SLOT(dev->devfn),
+				PCI_FUNC(dev->devfn));
+
+	if (!psdev || !psdev->pdev) {
+		dev_err(&dev->dev,
+			DRV_NAME " device is not found/assigned\n");
+		goto end;
+	}
+
+	if (!psdev->pdev->sh_info) {
+		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
+			" by HVM, kill it\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+
+	/*Guest owns the device yet no aer handler regiested, kill guest*/
+	if (!test_bit(_XEN_PCIB_AERHANDLER,
+		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		dev_dbg(&dev->dev, "guest may have no aer driver, kill it\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+	result = common_process(psdev, error, XEN_PCI_OP_aer_detected, result);
+
+	if (result == PCI_ERS_RESULT_NONE ||
+		result == PCI_ERS_RESULT_DISCONNECT) {
+		dev_dbg(&dev->dev,
+			"No AER error_detected service or disconnected!\n");
+		kill_domain_by_device(psdev);
+	}
+release:
+	pcistub_device_put(psdev);
+end:
+	up_write(&pcistub_sem);
+	return result;
+}
+
+/*xen_pcibk_error_resume: it will send the error_resume request to  pcifront
+* in case of the device driver could provide this service, and then wait
+* for pcifront ack.
+* @dev: pointer to PCI devices
+*/
+
+static void xen_pcibk_error_resume(struct pci_dev *dev)
+{
+	struct pcistub_device *psdev;
+
+	dev_dbg(&dev->dev, "xen_pcibk_error_resume(bus:%x,devfn:%x)\n",
+		dev->bus->number, dev->devfn);
+
+	down_write(&pcistub_sem);
+	psdev = pcistub_device_find(pci_domain_nr(dev->bus),
+				dev->bus->number,
+				PCI_SLOT(dev->devfn),
+				PCI_FUNC(dev->devfn));
+
+	if (!psdev || !psdev->pdev) {
+		dev_err(&dev->dev,
+			DRV_NAME " device is not found/assigned\n");
+		goto end;
+	}
+
+	if (!psdev->pdev->sh_info) {
+		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
+			" by HVM, kill it\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+
+	if (!test_bit(_XEN_PCIB_AERHANDLER,
+		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		dev_err(&dev->dev,
+			"guest with no AER driver should have been killed\n");
+		kill_domain_by_device(psdev);
+		goto release;
+	}
+	common_process(psdev, 1, XEN_PCI_OP_aer_resume,
+		       PCI_ERS_RESULT_RECOVERED);
+release:
+	pcistub_device_put(psdev);
+end:
+	up_write(&pcistub_sem);
+	return;
+}
+
+/*add xen_pcibk AER handling*/
+static struct pci_error_handlers xen_pcibk_error_handler = {
+	.error_detected = xen_pcibk_error_detected,
+	.mmio_enabled = xen_pcibk_mmio_enabled,
+	.slot_reset = xen_pcibk_slot_reset,
+	.resume = xen_pcibk_error_resume,
+};
+
+/*
+ * Note: There is no MODULE_DEVICE_TABLE entry here because this isn't
+ * for a normal device. I don't want it to be loaded automatically.
+ */
+
+static struct pci_driver xen_pcibk_pci_driver = {
+	/* The name should be xen_pciback, but until the tools are updated
+	 * we will keep it as pciback. */
+	.name = "pciback",
+	.id_table = pcistub_ids,
+	.probe = pcistub_probe,
+	.remove = pcistub_remove,
+	.err_handler = &xen_pcibk_error_handler,
+};
+
+static inline int str_to_slot(const char *buf, int *domain, int *bus,
+			      int *slot, int *func)
+{
+	int err;
+
+	err = sscanf(buf, " %x:%x:%x.%x", domain, bus, slot, func);
+	if (err == 4)
+		return 0;
+	else if (err < 0)
+		return -EINVAL;
+
+	/* try again without domain */
+	*domain = 0;
+	err = sscanf(buf, " %x:%x.%x", bus, slot, func);
+	if (err == 3)
+		return 0;
+
+	return -EINVAL;
+}
+
+static inline int str_to_quirk(const char *buf, int *domain, int *bus, int
+			       *slot, int *func, int *reg, int *size, int *mask)
+{
+	int err;
+
+	err =
+	    sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot,
+		   func, reg, size, mask);
+	if (err == 7)
+		return 0;
+	return -EINVAL;
+}
+
+static int pcistub_device_id_add(int domain, int bus, int slot, int func)
+{
+	struct pcistub_device_id *pci_dev_id;
+	unsigned long flags;
+
+	pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL);
+	if (!pci_dev_id)
+		return -ENOMEM;
+
+	pci_dev_id->domain = domain;
+	pci_dev_id->bus = bus;
+	pci_dev_id->devfn = PCI_DEVFN(slot, func);
+
+	pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n",
+		 domain, bus, slot, func);
+
+	spin_lock_irqsave(&device_ids_lock, flags);
+	list_add_tail(&pci_dev_id->slot_list, &pcistub_device_ids);
+	spin_unlock_irqrestore(&device_ids_lock, flags);
+
+	return 0;
+}
+
+static int pcistub_device_id_remove(int domain, int bus, int slot, int func)
+{
+	struct pcistub_device_id *pci_dev_id, *t;
+	int devfn = PCI_DEVFN(slot, func);
+	int err = -ENOENT;
+	unsigned long flags;
+
+	spin_lock_irqsave(&device_ids_lock, flags);
+	list_for_each_entry_safe(pci_dev_id, t, &pcistub_device_ids,
+				 slot_list) {
+		if (pci_dev_id->domain == domain
+		    && pci_dev_id->bus == bus && pci_dev_id->devfn == devfn) {
+			/* Don't break; here because it's possible the same
+			 * slot could be in the list more than once
+			 */
+			list_del(&pci_dev_id->slot_list);
+			kfree(pci_dev_id);
+
+			err = 0;
+
+			pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%d from "
+				 "seize list\n", domain, bus, slot, func);
+		}
+	}
+	spin_unlock_irqrestore(&device_ids_lock, flags);
+
+	return err;
+}
+
+static int pcistub_reg_add(int domain, int bus, int slot, int func, int reg,
+			   int size, int mask)
+{
+	int err = 0;
+	struct pcistub_device *psdev;
+	struct pci_dev *dev;
+	struct config_field *field;
+
+	psdev = pcistub_device_find(domain, bus, slot, func);
+	if (!psdev || !psdev->dev) {
+		err = -ENODEV;
+		goto out;
+	}
+	dev = psdev->dev;
+
+	field = kzalloc(sizeof(*field), GFP_ATOMIC);
+	if (!field) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	field->offset = reg;
+	field->size = size;
+	field->mask = mask;
+	field->init = NULL;
+	field->reset = NULL;
+	field->release = NULL;
+	field->clean = xen_pcibk_config_field_free;
+
+	err = xen_pcibk_config_quirks_add_field(dev, field);
+	if (err)
+		kfree(field);
+out:
+	return err;
+}
+
+static ssize_t pcistub_slot_add(struct device_driver *drv, const char *buf,
+				size_t count)
+{
+	int domain, bus, slot, func;
+	int err;
+
+	err = str_to_slot(buf, &domain, &bus, &slot, &func);
+	if (err)
+		goto out;
+
+	err = pcistub_device_id_add(domain, bus, slot, func);
+
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+static DRIVER_ATTR(new_slot, S_IWUSR, NULL, pcistub_slot_add);
+
+static ssize_t pcistub_slot_remove(struct device_driver *drv, const char *buf,
+				   size_t count)
+{
+	int domain, bus, slot, func;
+	int err;
+
+	err = str_to_slot(buf, &domain, &bus, &slot, &func);
+	if (err)
+		goto out;
+
+	err = pcistub_device_id_remove(domain, bus, slot, func);
+
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+static DRIVER_ATTR(remove_slot, S_IWUSR, NULL, pcistub_slot_remove);
+
+static ssize_t pcistub_slot_show(struct device_driver *drv, char *buf)
+{
+	struct pcistub_device_id *pci_dev_id;
+	size_t count = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&device_ids_lock, flags);
+	list_for_each_entry(pci_dev_id, &pcistub_device_ids, slot_list) {
+		if (count >= PAGE_SIZE)
+			break;
+
+		count += scnprintf(buf + count, PAGE_SIZE - count,
+				   "%04x:%02x:%02x.%d\n",
+				   pci_dev_id->domain, pci_dev_id->bus,
+				   PCI_SLOT(pci_dev_id->devfn),
+				   PCI_FUNC(pci_dev_id->devfn));
+	}
+	spin_unlock_irqrestore(&device_ids_lock, flags);
+
+	return count;
+}
+static DRIVER_ATTR(slots, S_IRUSR, pcistub_slot_show, NULL);
+
+static ssize_t pcistub_irq_handler_show(struct device_driver *drv, char *buf)
+{
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+	size_t count = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (count >= PAGE_SIZE)
+			break;
+		if (!psdev->dev)
+			continue;
+		dev_data = pci_get_drvdata(psdev->dev);
+		if (!dev_data)
+			continue;
+		count +=
+		    scnprintf(buf + count, PAGE_SIZE - count,
+			      "%s:%s:%sing:%ld\n",
+			      pci_name(psdev->dev),
+			      dev_data->isr_on ? "on" : "off",
+			      dev_data->ack_intr ? "ack" : "not ack",
+			      dev_data->handled);
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return count;
+}
+static DRIVER_ATTR(irq_handlers, S_IRUSR, pcistub_irq_handler_show, NULL);
+
+static ssize_t pcistub_irq_handler_switch(struct device_driver *drv,
+					  const char *buf,
+					  size_t count)
+{
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+	int domain, bus, slot, func;
+	int err = -ENOENT;
+
+	err = str_to_slot(buf, &domain, &bus, &slot, &func);
+	if (err)
+		goto out;
+
+	psdev = pcistub_device_find(domain, bus, slot, func);
+
+	if (!psdev)
+		goto out;
+
+	dev_data = pci_get_drvdata(psdev->dev);
+	if (!dev_data)
+		goto out;
+
+	dev_dbg(&psdev->dev->dev, "%s fake irq handler: %d->%d\n",
+		dev_data->irq_name, dev_data->isr_on,
+		!dev_data->isr_on);
+
+	dev_data->isr_on = !(dev_data->isr_on);
+	if (dev_data->isr_on)
+		dev_data->ack_intr = 1;
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+static DRIVER_ATTR(irq_handler_state, S_IWUSR, NULL,
+		   pcistub_irq_handler_switch);
+
+static ssize_t pcistub_quirk_add(struct device_driver *drv, const char *buf,
+				 size_t count)
+{
+	int domain, bus, slot, func, reg, size, mask;
+	int err;
+
+	err = str_to_quirk(buf, &domain, &bus, &slot, &func, &reg, &size,
+			   &mask);
+	if (err)
+		goto out;
+
+	err = pcistub_reg_add(domain, bus, slot, func, reg, size, mask);
+
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+
+static ssize_t pcistub_quirk_show(struct device_driver *drv, char *buf)
+{
+	int count = 0;
+	unsigned long flags;
+	struct xen_pcibk_config_quirk *quirk;
+	struct xen_pcibk_dev_data *dev_data;
+	const struct config_field *field;
+	const struct config_field_entry *cfg_entry;
+
+	spin_lock_irqsave(&device_ids_lock, flags);
+	list_for_each_entry(quirk, &xen_pcibk_quirks, quirks_list) {
+		if (count >= PAGE_SIZE)
+			goto out;
+
+		count += scnprintf(buf + count, PAGE_SIZE - count,
+				   "%02x:%02x.%01x\n\t%04x:%04x:%04x:%04x\n",
+				   quirk->pdev->bus->number,
+				   PCI_SLOT(quirk->pdev->devfn),
+				   PCI_FUNC(quirk->pdev->devfn),
+				   quirk->devid.vendor, quirk->devid.device,
+				   quirk->devid.subvendor,
+				   quirk->devid.subdevice);
+
+		dev_data = pci_get_drvdata(quirk->pdev);
+
+		list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+			field = cfg_entry->field;
+			if (count >= PAGE_SIZE)
+				goto out;
+
+			count += scnprintf(buf + count, PAGE_SIZE - count,
+					   "\t\t%08x:%01x:%08x\n",
+					   cfg_entry->base_offset +
+					   field->offset, field->size,
+					   field->mask);
+		}
+	}
+
+out:
+	spin_unlock_irqrestore(&device_ids_lock, flags);
+
+	return count;
+}
+static DRIVER_ATTR(quirks, S_IRUSR | S_IWUSR, pcistub_quirk_show,
+		   pcistub_quirk_add);
+
+static ssize_t permissive_add(struct device_driver *drv, const char *buf,
+			      size_t count)
+{
+	int domain, bus, slot, func;
+	int err;
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+	err = str_to_slot(buf, &domain, &bus, &slot, &func);
+	if (err)
+		goto out;
+	psdev = pcistub_device_find(domain, bus, slot, func);
+	if (!psdev) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (!psdev->dev) {
+		err = -ENODEV;
+		goto release;
+	}
+	dev_data = pci_get_drvdata(psdev->dev);
+	/* the driver data for a device should never be null at this point */
+	if (!dev_data) {
+		err = -ENXIO;
+		goto release;
+	}
+	if (!dev_data->permissive) {
+		dev_data->permissive = 1;
+		/* Let user know that what they're doing could be unsafe */
+		dev_warn(&psdev->dev->dev, "enabling permissive mode "
+			 "configuration space accesses!\n");
+		dev_warn(&psdev->dev->dev,
+			 "permissive mode is potentially unsafe!\n");
+	}
+release:
+	pcistub_device_put(psdev);
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+
+static ssize_t permissive_show(struct device_driver *drv, char *buf)
+{
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+	size_t count = 0;
+	unsigned long flags;
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (count >= PAGE_SIZE)
+			break;
+		if (!psdev->dev)
+			continue;
+		dev_data = pci_get_drvdata(psdev->dev);
+		if (!dev_data || !dev_data->permissive)
+			continue;
+		count +=
+		    scnprintf(buf + count, PAGE_SIZE - count, "%s\n",
+			      pci_name(psdev->dev));
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return count;
+}
+static DRIVER_ATTR(permissive, S_IRUSR | S_IWUSR, permissive_show,
+		   permissive_add);
+
+static void pcistub_exit(void)
+{
+	driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_new_slot);
+	driver_remove_file(&xen_pcibk_pci_driver.driver,
+			   &driver_attr_remove_slot);
+	driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_slots);
+	driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_quirks);
+	driver_remove_file(&xen_pcibk_pci_driver.driver,
+			   &driver_attr_permissive);
+	driver_remove_file(&xen_pcibk_pci_driver.driver,
+			   &driver_attr_irq_handlers);
+	driver_remove_file(&xen_pcibk_pci_driver.driver,
+			   &driver_attr_irq_handler_state);
+	pci_unregister_driver(&xen_pcibk_pci_driver);
+}
+
+static int __init pcistub_init(void)
+{
+	int pos = 0;
+	int err = 0;
+	int domain, bus, slot, func;
+	int parsed;
+
+	if (pci_devs_to_hide && *pci_devs_to_hide) {
+		do {
+			parsed = 0;
+
+			err = sscanf(pci_devs_to_hide + pos,
+				     " (%x:%x:%x.%x) %n",
+				     &domain, &bus, &slot, &func, &parsed);
+			if (err != 4) {
+				domain = 0;
+				err = sscanf(pci_devs_to_hide + pos,
+					     " (%x:%x.%x) %n",
+					     &bus, &slot, &func, &parsed);
+				if (err != 3)
+					goto parse_error;
+			}
+
+			err = pcistub_device_id_add(domain, bus, slot, func);
+			if (err)
+				goto out;
+
+			/* if parsed<=0, we've reached the end of the string */
+			pos += parsed;
+		} while (parsed > 0 && pci_devs_to_hide[pos]);
+	}
+
+	/* If we're the first PCI Device Driver to register, we're the
+	 * first one to get offered PCI devices as they become
+	 * available (and thus we can be the first to grab them)
+	 */
+	err = pci_register_driver(&xen_pcibk_pci_driver);
+	if (err < 0)
+		goto out;
+
+	err = driver_create_file(&xen_pcibk_pci_driver.driver,
+				 &driver_attr_new_slot);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_remove_slot);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_slots);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_quirks);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_permissive);
+
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_irq_handlers);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					&driver_attr_irq_handler_state);
+	if (err)
+		pcistub_exit();
+
+out:
+	return err;
+
+parse_error:
+	printk(KERN_ERR DRV_NAME ": Error parsing pci_devs_to_hide at \"%s\"\n",
+	       pci_devs_to_hide + pos);
+	return -EINVAL;
+}
+
+#ifndef MODULE
+/*
+ * fs_initcall happens before device_initcall
+ * so xen_pcibk *should* get called first (b/c we
+ * want to suck up any device before other drivers
+ * get a chance by being the first pci device
+ * driver to register)
+ */
+fs_initcall(pcistub_init);
+#endif
+
+static int __init xen_pcibk_init(void)
+{
+	int err;
+
+	if (!xen_initial_domain())
+		return -ENODEV;
+
+	err = xen_pcibk_config_init();
+	if (err)
+		return err;
+
+#ifdef MODULE
+	err = pcistub_init();
+	if (err < 0)
+		return err;
+#endif
+
+	pcistub_init_devices_late();
+	err = xen_pcibk_xenbus_register();
+	if (err)
+		pcistub_exit();
+
+	return err;
+}
+
+static void __exit xen_pcibk_cleanup(void)
+{
+	xen_pcibk_xenbus_unregister();
+	pcistub_exit();
+}
+
+module_init(xen_pcibk_init);
+module_exit(xen_pcibk_cleanup);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_ALIAS("xen-backend:pci");
diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h
new file mode 100644
index 00000000..a7def010
--- /dev/null
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -0,0 +1,192 @@
+/*
+ * PCI Backend Common Data Structures & Function Declarations
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCIBACK_H__
+#define __XEN_PCIBACK_H__
+
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <xen/xenbus.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/atomic.h>
+#include <xen/interface/io/pciif.h>
+
+#define DRV_NAME	"xen-pciback"
+
+struct pci_dev_entry {
+	struct list_head list;
+	struct pci_dev *dev;
+};
+
+#define _PDEVF_op_active	(0)
+#define PDEVF_op_active		(1<<(_PDEVF_op_active))
+#define _PCIB_op_pending	(1)
+#define PCIB_op_pending		(1<<(_PCIB_op_pending))
+
+struct xen_pcibk_device {
+	void *pci_dev_data;
+	struct mutex dev_lock;
+	struct xenbus_device *xdev;
+	struct xenbus_watch be_watch;
+	u8 be_watching;
+	int evtchn_irq;
+	struct xen_pci_sharedinfo *sh_info;
+	unsigned long flags;
+	struct work_struct op_work;
+};
+
+struct xen_pcibk_dev_data {
+	struct list_head config_fields;
+	struct pci_saved_state *pci_saved_state;
+	unsigned int permissive:1;
+	unsigned int warned_on_write:1;
+	unsigned int enable_intx:1;
+	unsigned int isr_on:1; /* Whether the IRQ handler is installed. */
+	unsigned int ack_intr:1; /* .. and ACK-ing */
+	unsigned long handled;
+	unsigned int irq; /* Saved in case device transitions to MSI/MSI-X */
+	char irq_name[0]; /* xen-pcibk[000:04:00.0] */
+};
+
+/* Used by XenBus and xen_pcibk_ops.c */
+extern wait_queue_head_t xen_pcibk_aer_wait_queue;
+extern struct workqueue_struct *xen_pcibk_wq;
+/* Used by pcistub.c and conf_space_quirks.c */
+extern struct list_head xen_pcibk_quirks;
+
+/* Get/Put PCI Devices that are hidden from the PCI Backend Domain */
+struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
+					    int domain, int bus,
+					    int slot, int func);
+struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
+				    struct pci_dev *dev);
+void pcistub_put_pci_dev(struct pci_dev *dev);
+
+/* Ensure a device is turned off or reset */
+void xen_pcibk_reset_device(struct pci_dev *pdev);
+
+/* Access a virtual configuration space for a PCI device */
+int xen_pcibk_config_init(void);
+int xen_pcibk_config_init_dev(struct pci_dev *dev);
+void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev);
+void xen_pcibk_config_reset_dev(struct pci_dev *dev);
+void xen_pcibk_config_free_dev(struct pci_dev *dev);
+int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
+			  u32 *ret_val);
+int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size,
+			   u32 value);
+
+/* Handle requests for specific devices from the frontend */
+typedef int (*publish_pci_dev_cb) (struct xen_pcibk_device *pdev,
+				   unsigned int domain, unsigned int bus,
+				   unsigned int devfn, unsigned int devid);
+typedef int (*publish_pci_root_cb) (struct xen_pcibk_device *pdev,
+				    unsigned int domain, unsigned int bus);
+
+/* Backend registration for the two types of BDF representation:
+ *  vpci - BDFs start at 00
+ *  passthrough - BDFs are exactly like in the host.
+ */
+struct xen_pcibk_backend {
+	const char *name;
+	int (*init)(struct xen_pcibk_device *pdev);
+	void (*free)(struct xen_pcibk_device *pdev);
+	int (*find)(struct pci_dev *pcidev, struct xen_pcibk_device *pdev,
+		    unsigned int *domain, unsigned int *bus,
+		    unsigned int *devfn);
+	int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb);
+	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev);
+	int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
+		   int devid, publish_pci_dev_cb publish_cb);
+	struct pci_dev *(*get)(struct xen_pcibk_device *pdev,
+			       unsigned int domain, unsigned int bus,
+			       unsigned int devfn);
+};
+
+extern const struct xen_pcibk_backend xen_pcibk_vpci_backend;
+extern const struct xen_pcibk_backend xen_pcibk_passthrough_backend;
+extern const struct xen_pcibk_backend *xen_pcibk_backend;
+
+static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev,
+					int devid,
+					publish_pci_dev_cb publish_cb)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->add)
+		return xen_pcibk_backend->add(pdev, dev, devid, publish_cb);
+	return -1;
+}
+
+static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					     struct pci_dev *dev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->free)
+		return xen_pcibk_backend->release(pdev, dev);
+}
+
+static inline struct pci_dev *
+xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, unsigned int domain,
+		      unsigned int bus, unsigned int devfn)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->get)
+		return xen_pcibk_backend->get(pdev, domain, bus, devfn);
+	return NULL;
+}
+
+/**
+* Add for domain0 PCIE-AER handling. Get guest domain/bus/devfn in xen_pcibk
+* before sending aer request to pcifront, so that guest could identify
+* device, coopearte with xen_pcibk to finish aer recovery job if device driver
+* has the capability
+*/
+static inline int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					     struct xen_pcibk_device *pdev,
+					     unsigned int *domain,
+					     unsigned int *bus,
+					     unsigned int *devfn)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->find)
+		return xen_pcibk_backend->find(pcidev, pdev, domain, bus,
+					       devfn);
+	return -1;
+}
+
+static inline int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->init)
+		return xen_pcibk_backend->init(pdev);
+	return -1;
+}
+
+static inline int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					      publish_pci_root_cb cb)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->publish)
+		return xen_pcibk_backend->publish(pdev, cb);
+	return -1;
+}
+
+static inline void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->free)
+		return xen_pcibk_backend->free(pdev);
+}
+
+/* Handles events from front-end */
+irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id);
+void xen_pcibk_do_op(struct work_struct *data);
+
+int xen_pcibk_xenbus_register(void);
+void xen_pcibk_xenbus_unregister(void);
+
+extern int verbose_request;
+
+void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev);
+#endif
+
+/* Handles shared IRQs that can to device domain and control domain. */
+void xen_pcibk_irq_handler(struct pci_dev *dev, int reset);
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
new file mode 100644
index 00000000..97f5d264
--- /dev/null
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -0,0 +1,383 @@
+/*
+ * PCI Backend Operations - respond to PCI requests from Frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/bitops.h>
+#include <xen/events.h>
+#include <linux/sched.h>
+#include "pciback.h"
+
+int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id);
+
+/* Ensure a device is has the fake IRQ handler "turned on/off" and is
+ * ready to be exported. This MUST be run after xen_pcibk_reset_device
+ * which does the actual PCI device enable/disable.
+ */
+static void xen_pcibk_control_isr(struct pci_dev *dev, int reset)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int rc;
+	int enable = 0;
+
+	dev_data = pci_get_drvdata(dev);
+	if (!dev_data)
+		return;
+
+	/* We don't deal with bridges */
+	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
+		return;
+
+	if (reset) {
+		dev_data->enable_intx = 0;
+		dev_data->ack_intr = 0;
+	}
+	enable =  dev_data->enable_intx;
+
+	/* Asked to disable, but ISR isn't runnig */
+	if (!enable && !dev_data->isr_on)
+		return;
+
+	/* Squirrel away the IRQs in the dev_data. We need this
+	 * b/c when device transitions to MSI, the dev->irq is
+	 * overwritten with the MSI vector.
+	 */
+	if (enable)
+		dev_data->irq = dev->irq;
+
+	/*
+	 * SR-IOV devices in all use MSI-X and have no legacy
+	 * interrupts, so inhibit creating a fake IRQ handler for them.
+	 */
+	if (dev_data->irq == 0)
+		goto out;
+
+	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s-> %s\n",
+		dev_data->irq_name,
+		dev_data->irq,
+		pci_is_enabled(dev) ? "on" : "off",
+		dev->msi_enabled ? "MSI" : "",
+		dev->msix_enabled ? "MSI/X" : "",
+		dev_data->isr_on ? "enable" : "disable",
+		enable ? "enable" : "disable");
+
+	if (enable) {
+		rc = request_irq(dev_data->irq,
+				xen_pcibk_guest_interrupt, IRQF_SHARED,
+				dev_data->irq_name, dev);
+		if (rc) {
+			dev_err(&dev->dev, "%s: failed to install fake IRQ " \
+				"handler for IRQ %d! (rc:%d)\n",
+				dev_data->irq_name, dev_data->irq, rc);
+			goto out;
+		}
+	} else {
+		free_irq(dev_data->irq, dev);
+		dev_data->irq = 0;
+	}
+	dev_data->isr_on = enable;
+	dev_data->ack_intr = enable;
+out:
+	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s\n",
+		dev_data->irq_name,
+		dev_data->irq,
+		pci_is_enabled(dev) ? "on" : "off",
+		dev->msi_enabled ? "MSI" : "",
+		dev->msix_enabled ? "MSI/X" : "",
+		enable ? (dev_data->isr_on ? "enabled" : "failed to enable") :
+			(dev_data->isr_on ? "failed to disable" : "disabled"));
+}
+
+/* Ensure a device is "turned off" and ready to be exported.
+ * (Also see xen_pcibk_config_reset to ensure virtual configuration space is
+ * ready to be re-exported)
+ */
+void xen_pcibk_reset_device(struct pci_dev *dev)
+{
+	u16 cmd;
+
+	xen_pcibk_control_isr(dev, 1 /* reset device */);
+
+	/* Disable devices (but not bridges) */
+	if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
+#ifdef CONFIG_PCI_MSI
+		/* The guest could have been abruptly killed without
+		 * disabling MSI/MSI-X interrupts.*/
+		if (dev->msix_enabled)
+			pci_disable_msix(dev);
+		if (dev->msi_enabled)
+			pci_disable_msi(dev);
+#endif
+		pci_disable_device(dev);
+
+		pci_write_config_word(dev, PCI_COMMAND, 0);
+
+		dev->is_busmaster = 0;
+	} else {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & (PCI_COMMAND_INVALIDATE)) {
+			cmd &= ~(PCI_COMMAND_INVALIDATE);
+			pci_write_config_word(dev, PCI_COMMAND, cmd);
+
+			dev->is_busmaster = 0;
+		}
+	}
+}
+
+#ifdef CONFIG_PCI_MSI
+static
+int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev,
+			 struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int otherend = pdev->xdev->otherend_id;
+	int status;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI\n", pci_name(dev));
+
+	status = pci_enable_msi(dev);
+
+	if (status) {
+		printk(KERN_ERR "error enable msi for guest %x status %x\n",
+			otherend, status);
+		op->value = 0;
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* The value the guest needs is actually the IDT vector, not the
+	 * the local domain's IRQ number. */
+
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
+			op->value);
+
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 0;
+
+	return 0;
+}
+
+static
+int xen_pcibk_disable_msi(struct xen_pcibk_device *pdev,
+			  struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI\n",
+		       pci_name(dev));
+	pci_disable_msi(dev);
+
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
+			op->value);
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 1;
+	return 0;
+}
+
+static
+int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
+			  struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int i, result;
+	struct msix_entry *entries;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n",
+		       pci_name(dev));
+	if (op->value > SH_INFO_MAX_VEC)
+		return -EINVAL;
+
+	entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL);
+	if (entries == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < op->value; i++) {
+		entries[i].entry = op->msix_entries[i].entry;
+		entries[i].vector = op->msix_entries[i].vector;
+	}
+
+	result = pci_enable_msix(dev, entries, op->value);
+
+	if (result == 0) {
+		for (i = 0; i < op->value; i++) {
+			op->msix_entries[i].entry = entries[i].entry;
+			if (entries[i].vector)
+				op->msix_entries[i].vector =
+					xen_pirq_from_irq(entries[i].vector);
+				if (unlikely(verbose_request))
+					printk(KERN_DEBUG DRV_NAME ": %s: " \
+						"MSI-X[%d]: %d\n",
+						pci_name(dev), i,
+						op->msix_entries[i].vector);
+		}
+	} else {
+		printk(KERN_WARNING DRV_NAME ": %s: failed to enable MSI-X: err %d!\n",
+			pci_name(dev), result);
+	}
+	kfree(entries);
+
+	op->value = result;
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 0;
+
+	return result > 0 ? 0 : result;
+}
+
+static
+int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev,
+			   struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI-X\n",
+			pci_name(dev));
+	pci_disable_msix(dev);
+
+	/*
+	 * SR-IOV devices (which don't have any legacy IRQ) have
+	 * an undefined IRQ value of zero.
+	 */
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n", pci_name(dev),
+			op->value);
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 1;
+	return 0;
+}
+#endif
+/*
+* Now the same evtchn is used for both pcifront conf_read_write request
+* as well as pcie aer front end ack. We use a new work_queue to schedule
+* xen_pcibk conf_read_write service for avoiding confict with aer_core
+* do_recovery job which also use the system default work_queue
+*/
+void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev)
+{
+	/* Check that frontend is requesting an operation and that we are not
+	 * already processing a request */
+	if (test_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags)
+	    && !test_and_set_bit(_PDEVF_op_active, &pdev->flags)) {
+		queue_work(xen_pcibk_wq, &pdev->op_work);
+	}
+	/*_XEN_PCIB_active should have been cleared by pcifront. And also make
+	sure xen_pcibk is waiting for ack by checking _PCIB_op_pending*/
+	if (!test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+	    && test_bit(_PCIB_op_pending, &pdev->flags)) {
+		wake_up(&xen_pcibk_aer_wait_queue);
+	}
+}
+
+/* Performing the configuration space reads/writes must not be done in atomic
+ * context because some of the pci_* functions can sleep (mostly due to ACPI
+ * use of semaphores). This function is intended to be called from a work
+ * queue in process context taking a struct xen_pcibk_device as a parameter */
+
+void xen_pcibk_do_op(struct work_struct *data)
+{
+	struct xen_pcibk_device *pdev =
+		container_of(data, struct xen_pcibk_device, op_work);
+	struct pci_dev *dev;
+	struct xen_pcibk_dev_data *dev_data = NULL;
+	struct xen_pci_op *op = &pdev->sh_info->op;
+	int test_intx = 0;
+
+	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);
+
+	if (dev == NULL)
+		op->err = XEN_PCI_ERR_dev_not_found;
+	else {
+		dev_data = pci_get_drvdata(dev);
+		if (dev_data)
+			test_intx = dev_data->enable_intx;
+		switch (op->cmd) {
+		case XEN_PCI_OP_conf_read:
+			op->err = xen_pcibk_config_read(dev,
+				  op->offset, op->size, &op->value);
+			break;
+		case XEN_PCI_OP_conf_write:
+			op->err = xen_pcibk_config_write(dev,
+				  op->offset, op->size,	op->value);
+			break;
+#ifdef CONFIG_PCI_MSI
+		case XEN_PCI_OP_enable_msi:
+			op->err = xen_pcibk_enable_msi(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_disable_msi:
+			op->err = xen_pcibk_disable_msi(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_enable_msix:
+			op->err = xen_pcibk_enable_msix(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_disable_msix:
+			op->err = xen_pcibk_disable_msix(pdev, dev, op);
+			break;
+#endif
+		default:
+			op->err = XEN_PCI_ERR_not_implemented;
+			break;
+		}
+	}
+	if (!op->err && dev && dev_data) {
+		/* Transition detected */
+		if ((dev_data->enable_intx != test_intx))
+			xen_pcibk_control_isr(dev, 0 /* no reset */);
+	}
+	/* Tell the driver domain that we're done. */
+	wmb();
+	clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_irq(pdev->evtchn_irq);
+
+	/* Mark that we're done. */
+	smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */
+	clear_bit(_PDEVF_op_active, &pdev->flags);
+	smp_mb__after_clear_bit(); /* /before/ final check for work */
+
+	/* Check to see if the driver domain tried to start another request in
+	 * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.
+	*/
+	xen_pcibk_test_and_schedule_op(pdev);
+}
+
+irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id)
+{
+	struct xen_pcibk_device *pdev = dev_id;
+
+	xen_pcibk_test_and_schedule_op(pdev);
+
+	return IRQ_HANDLED;
+}
+static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id)
+{
+	struct pci_dev *dev = (struct pci_dev *)dev_id;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+
+	if (dev_data->isr_on && dev_data->ack_intr) {
+		dev_data->handled++;
+		if ((dev_data->handled % 1000) == 0) {
+			if (xen_test_irq_shared(irq)) {
+				printk(KERN_INFO "%s IRQ line is not shared "
+					"with other domains. Turning ISR off\n",
+					 dev_data->irq_name);
+				dev_data->ack_intr = 0;
+			}
+		}
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c
new file mode 100644
index 00000000..46d140ba
--- /dev/null
+++ b/drivers/xen/xen-pciback/vpci.c
@@ -0,0 +1,254 @@
+/*
+ * PCI Backend - Provides a Virtual PCI bus (with real devices)
+ *               to the frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/mutex.h>
+#include "pciback.h"
+
+#define PCI_SLOT_MAX 32
+
+struct vpci_dev_data {
+	/* Access to dev_list must be protected by lock */
+	struct list_head dev_list[PCI_SLOT_MAX];
+	struct mutex lock;
+};
+
+static inline struct list_head *list_first(struct list_head *head)
+{
+	return head->next;
+}
+
+static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
+					       unsigned int domain,
+					       unsigned int bus,
+					       unsigned int devfn)
+{
+	struct pci_dev_entry *entry;
+	struct pci_dev *dev = NULL;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+
+	if (domain != 0 || bus != 0)
+		return NULL;
+
+	if (PCI_SLOT(devfn) < PCI_SLOT_MAX) {
+		mutex_lock(&vpci_dev->lock);
+
+		list_for_each_entry(entry,
+				    &vpci_dev->dev_list[PCI_SLOT(devfn)],
+				    list) {
+			if (PCI_FUNC(entry->dev->devfn) == PCI_FUNC(devfn)) {
+				dev = entry->dev;
+				break;
+			}
+		}
+
+		mutex_unlock(&vpci_dev->lock);
+	}
+	return dev;
+}
+
+static inline int match_slot(struct pci_dev *l, struct pci_dev *r)
+{
+	if (pci_domain_nr(l->bus) == pci_domain_nr(r->bus)
+	    && l->bus == r->bus && PCI_SLOT(l->devfn) == PCI_SLOT(r->devfn))
+		return 1;
+
+	return 0;
+}
+
+static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
+				   struct pci_dev *dev, int devid,
+				   publish_pci_dev_cb publish_cb)
+{
+	int err = 0, slot, func = -1;
+	struct pci_dev_entry *t, *dev_entry;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+
+	if ((dev->class >> 24) == PCI_BASE_CLASS_BRIDGE) {
+		err = -EFAULT;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Can't export bridges on the virtual PCI bus");
+		goto out;
+	}
+
+	dev_entry = kmalloc(sizeof(*dev_entry), GFP_KERNEL);
+	if (!dev_entry) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error adding entry to virtual PCI bus");
+		goto out;
+	}
+
+	dev_entry->dev = dev;
+
+	mutex_lock(&vpci_dev->lock);
+
+	/* Keep multi-function devices together on the virtual PCI bus */
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		if (!list_empty(&vpci_dev->dev_list[slot])) {
+			t = list_entry(list_first(&vpci_dev->dev_list[slot]),
+				       struct pci_dev_entry, list);
+
+			if (match_slot(dev, t->dev)) {
+				pr_info(DRV_NAME ": vpci: %s: "
+					"assign to virtual slot %d func %d\n",
+					pci_name(dev), slot,
+					PCI_FUNC(dev->devfn));
+				list_add_tail(&dev_entry->list,
+					      &vpci_dev->dev_list[slot]);
+				func = PCI_FUNC(dev->devfn);
+				goto unlock;
+			}
+		}
+	}
+
+	/* Assign to a new slot on the virtual PCI bus */
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		if (list_empty(&vpci_dev->dev_list[slot])) {
+			printk(KERN_INFO DRV_NAME
+			       ": vpci: %s: assign to virtual slot %d\n",
+			       pci_name(dev), slot);
+			list_add_tail(&dev_entry->list,
+				      &vpci_dev->dev_list[slot]);
+			func = PCI_FUNC(dev->devfn);
+			goto unlock;
+		}
+	}
+
+	err = -ENOMEM;
+	xenbus_dev_fatal(pdev->xdev, err,
+			 "No more space on root virtual PCI bus");
+
+unlock:
+	mutex_unlock(&vpci_dev->lock);
+
+	/* Publish this device. */
+	if (!err)
+		err = publish_cb(pdev, 0, 0, PCI_DEVFN(slot, func), devid);
+
+out:
+	return err;
+}
+
+static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev)
+{
+	int slot;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+	struct pci_dev *found_dev = NULL;
+
+	mutex_lock(&vpci_dev->lock);
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		struct pci_dev_entry *e;
+
+		list_for_each_entry(e, &vpci_dev->dev_list[slot], list) {
+			if (e->dev == dev) {
+				list_del(&e->list);
+				found_dev = e->dev;
+				kfree(e);
+				goto out;
+			}
+		}
+	}
+
+out:
+	mutex_unlock(&vpci_dev->lock);
+
+	if (found_dev)
+		pcistub_put_pci_dev(found_dev);
+}
+
+static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+{
+	int slot;
+	struct vpci_dev_data *vpci_dev;
+
+	vpci_dev = kmalloc(sizeof(*vpci_dev), GFP_KERNEL);
+	if (!vpci_dev)
+		return -ENOMEM;
+
+	mutex_init(&vpci_dev->lock);
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++)
+		INIT_LIST_HEAD(&vpci_dev->dev_list[slot]);
+
+	pdev->pci_dev_data = vpci_dev;
+
+	return 0;
+}
+
+static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					 publish_pci_root_cb publish_cb)
+{
+	/* The Virtual PCI bus has only one root */
+	return publish_cb(pdev, 0, 0);
+}
+
+static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+{
+	int slot;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		struct pci_dev_entry *e, *tmp;
+		list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
+					 list) {
+			list_del(&e->list);
+			pcistub_put_pci_dev(e->dev);
+			kfree(e);
+		}
+	}
+
+	kfree(vpci_dev);
+	pdev->pci_dev_data = NULL;
+}
+
+static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					struct xen_pcibk_device *pdev,
+					unsigned int *domain, unsigned int *bus,
+					unsigned int *devfn)
+{
+	struct pci_dev_entry *entry;
+	struct pci_dev *dev = NULL;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+	int found = 0, slot;
+
+	mutex_lock(&vpci_dev->lock);
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		list_for_each_entry(entry,
+			    &vpci_dev->dev_list[slot],
+			    list) {
+			dev = entry->dev;
+			if (dev && dev->bus->number == pcidev->bus->number
+				&& pci_domain_nr(dev->bus) ==
+					pci_domain_nr(pcidev->bus)
+				&& dev->devfn == pcidev->devfn) {
+				found = 1;
+				*domain = 0;
+				*bus = 0;
+				*devfn = PCI_DEVFN(slot,
+					 PCI_FUNC(pcidev->devfn));
+			}
+		}
+	}
+	mutex_unlock(&vpci_dev->lock);
+	return found;
+}
+
+const struct xen_pcibk_backend xen_pcibk_vpci_backend = {
+	.name		= "vpci",
+	.init		= __xen_pcibk_init_devices,
+	.free		= __xen_pcibk_release_devices,
+	.find		= __xen_pcibk_get_pcifront_dev,
+	.publish	= __xen_pcibk_publish_pci_roots,
+	.release	= __xen_pcibk_release_pci_dev,
+	.add		= __xen_pcibk_add_pci_dev,
+	.get		= __xen_pcibk_get_pci_dev,
+};
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
new file mode 100644
index 00000000..64b11f99
--- /dev/null
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -0,0 +1,741 @@
+/*
+ * PCI Backend Xenbus Setup - handles setup with frontend and xend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/vmalloc.h>
+#include <linux/workqueue.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <asm/xen/pci.h>
+#include "pciback.h"
+
+#define INVALID_EVTCHN_IRQ  (-1)
+struct workqueue_struct *xen_pcibk_wq;
+
+static bool __read_mostly passthrough;
+module_param(passthrough, bool, S_IRUGO);
+MODULE_PARM_DESC(passthrough,
+	"Option to specify how to export PCI topology to guest:\n"\
+	" 0 - (default) Hide the true PCI topology and makes the frontend\n"\
+	"   there is a single PCI bus with only the exported devices on it.\n"\
+	"   For example, a device at 03:05.0 will be re-assigned to 00:00.0\n"\
+	"   while second device at 02:1a.1 will be re-assigned to 00:01.1.\n"\
+	" 1 - Passthrough provides a real view of the PCI topology to the\n"\
+	"   frontend (for example, a device at 06:01.b will still appear at\n"\
+	"   06:01.b to the frontend). This is similar to how Xen 2.0.x\n"\
+	"   exposed PCI devices to its driver domains. This may be required\n"\
+	"   for drivers which depend on finding their hardward in certain\n"\
+	"   bus/slot locations.");
+
+static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct xen_pcibk_device *pdev;
+
+	pdev = kzalloc(sizeof(struct xen_pcibk_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+	dev_dbg(&xdev->dev, "allocated pdev @ 0x%p\n", pdev);
+
+	pdev->xdev = xdev;
+	dev_set_drvdata(&xdev->dev, pdev);
+
+	mutex_init(&pdev->dev_lock);
+
+	pdev->sh_info = NULL;
+	pdev->evtchn_irq = INVALID_EVTCHN_IRQ;
+	pdev->be_watching = 0;
+
+	INIT_WORK(&pdev->op_work, xen_pcibk_do_op);
+
+	if (xen_pcibk_init_devices(pdev)) {
+		kfree(pdev);
+		pdev = NULL;
+	}
+out:
+	return pdev;
+}
+
+static void xen_pcibk_disconnect(struct xen_pcibk_device *pdev)
+{
+	mutex_lock(&pdev->dev_lock);
+	/* Ensure the guest can't trigger our handler before removing devices */
+	if (pdev->evtchn_irq != INVALID_EVTCHN_IRQ) {
+		unbind_from_irqhandler(pdev->evtchn_irq, pdev);
+		pdev->evtchn_irq = INVALID_EVTCHN_IRQ;
+	}
+
+	/* If the driver domain started an op, make sure we complete it
+	 * before releasing the shared memory */
+
+	/* Note, the workqueue does not use spinlocks at all.*/
+	flush_workqueue(xen_pcibk_wq);
+
+	if (pdev->sh_info != NULL) {
+		xenbus_unmap_ring_vfree(pdev->xdev, pdev->sh_info);
+		pdev->sh_info = NULL;
+	}
+	mutex_unlock(&pdev->dev_lock);
+}
+
+static void free_pdev(struct xen_pcibk_device *pdev)
+{
+	if (pdev->be_watching) {
+		unregister_xenbus_watch(&pdev->be_watch);
+		pdev->be_watching = 0;
+	}
+
+	xen_pcibk_disconnect(pdev);
+
+	xen_pcibk_release_devices(pdev);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+	pdev->xdev = NULL;
+
+	kfree(pdev);
+}
+
+static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref,
+			     int remote_evtchn)
+{
+	int err = 0;
+	void *vaddr;
+
+	dev_dbg(&pdev->xdev->dev,
+		"Attaching to frontend resources - gnt_ref=%d evtchn=%d\n",
+		gnt_ref, remote_evtchn);
+
+	err = xenbus_map_ring_valloc(pdev->xdev, gnt_ref, &vaddr);
+	if (err < 0) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				"Error mapping other domain page in ours.");
+		goto out;
+	}
+
+	pdev->sh_info = vaddr;
+
+	err = bind_interdomain_evtchn_to_irqhandler(
+		pdev->xdev->otherend_id, remote_evtchn, xen_pcibk_handle_event,
+		0, DRV_NAME, pdev);
+	if (err < 0) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error binding event channel to IRQ");
+		goto out;
+	}
+	pdev->evtchn_irq = err;
+	err = 0;
+
+	dev_dbg(&pdev->xdev->dev, "Attached!\n");
+out:
+	return err;
+}
+
+static int xen_pcibk_attach(struct xen_pcibk_device *pdev)
+{
+	int err = 0;
+	int gnt_ref, remote_evtchn;
+	char *magic = NULL;
+
+
+	mutex_lock(&pdev->dev_lock);
+	/* Make sure we only do this setup once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	/* Wait for frontend to state that it has published the configuration */
+	if (xenbus_read_driver_state(pdev->xdev->otherend) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "Reading frontend config\n");
+
+	err = xenbus_gather(XBT_NIL, pdev->xdev->otherend,
+			    "pci-op-ref", "%u", &gnt_ref,
+			    "event-channel", "%u", &remote_evtchn,
+			    "magic", NULL, &magic, NULL);
+	if (err) {
+		/* If configuration didn't get read correctly, wait longer */
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading configuration from frontend");
+		goto out;
+	}
+
+	if (magic == NULL || strcmp(magic, XEN_PCI_MAGIC) != 0) {
+		xenbus_dev_fatal(pdev->xdev, -EFAULT,
+				 "version mismatch (%s/%s) with pcifront - "
+				 "halting " DRV_NAME,
+				 magic, XEN_PCI_MAGIC);
+		goto out;
+	}
+
+	err = xen_pcibk_do_attach(pdev, gnt_ref, remote_evtchn);
+	if (err)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "Connecting...\n");
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+	if (err)
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to connected state!");
+
+	dev_dbg(&pdev->xdev->dev, "Connected? %d\n", err);
+out:
+	mutex_unlock(&pdev->dev_lock);
+
+	kfree(magic);
+
+	return err;
+}
+
+static int xen_pcibk_publish_pci_dev(struct xen_pcibk_device *pdev,
+				   unsigned int domain, unsigned int bus,
+				   unsigned int devfn, unsigned int devid)
+{
+	int err;
+	int len;
+	char str[64];
+
+	len = snprintf(str, sizeof(str), "vdev-%d", devid);
+	if (unlikely(len >= (sizeof(str) - 1))) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Note: The PV protocol uses %02x, don't change it */
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str,
+			    "%04x:%02x:%02x.%02x", domain, bus,
+			    PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+out:
+	return err;
+}
+
+static int xen_pcibk_export_device(struct xen_pcibk_device *pdev,
+				 int domain, int bus, int slot, int func,
+				 int devid)
+{
+	struct pci_dev *dev;
+	int err = 0;
+
+	dev_dbg(&pdev->xdev->dev, "exporting dom %x bus %x slot %x func %x\n",
+		domain, bus, slot, func);
+
+	dev = pcistub_get_pci_dev_by_slot(pdev, domain, bus, slot, func);
+	if (!dev) {
+		err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Couldn't locate PCI device "
+				 "(%04x:%02x:%02x.%d)! "
+				 "perhaps already in-use?",
+				 domain, bus, slot, func);
+		goto out;
+	}
+
+	err = xen_pcibk_add_pci_dev(pdev, dev, devid,
+				    xen_pcibk_publish_pci_dev);
+	if (err)
+		goto out;
+
+	dev_dbg(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
+	if (xen_register_device_domain_owner(dev,
+					     pdev->xdev->otherend_id) != 0) {
+		dev_err(&dev->dev, "Stealing ownership from dom%d.\n",
+			xen_find_device_domain_owner(dev));
+		xen_unregister_device_domain_owner(dev);
+		xen_register_device_domain_owner(dev, pdev->xdev->otherend_id);
+	}
+
+	/* TODO: It'd be nice to export a bridge and have all of its children
+	 * get exported with it. This may be best done in xend (which will
+	 * have to calculate resource usage anyway) but we probably want to
+	 * put something in here to ensure that if a bridge gets given to a
+	 * driver domain, that all devices under that bridge are not given
+	 * to other driver domains (as he who controls the bridge can disable
+	 * it and stop the other devices from working).
+	 */
+out:
+	return err;
+}
+
+static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
+				 int domain, int bus, int slot, int func)
+{
+	int err = 0;
+	struct pci_dev *dev;
+
+	dev_dbg(&pdev->xdev->dev, "removing dom %x bus %x slot %x func %x\n",
+		domain, bus, slot, func);
+
+	dev = xen_pcibk_get_pci_dev(pdev, domain, bus, PCI_DEVFN(slot, func));
+	if (!dev) {
+		err = -EINVAL;
+		dev_dbg(&pdev->xdev->dev, "Couldn't locate PCI device "
+			"(%04x:%02x:%02x.%d)! not owned by this domain\n",
+			domain, bus, slot, func);
+		goto out;
+	}
+
+	dev_dbg(&dev->dev, "unregistering for %d\n", pdev->xdev->otherend_id);
+	xen_unregister_device_domain_owner(dev);
+
+	xen_pcibk_release_pci_dev(pdev, dev);
+
+out:
+	return err;
+}
+
+static int xen_pcibk_publish_pci_root(struct xen_pcibk_device *pdev,
+				    unsigned int domain, unsigned int bus)
+{
+	unsigned int d, b;
+	int i, root_num, len, err;
+	char str[64];
+
+	dev_dbg(&pdev->xdev->dev, "Publishing pci roots\n");
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+			   "root_num", "%d", &root_num);
+	if (err == 0 || err == -ENOENT)
+		root_num = 0;
+	else if (err < 0)
+		goto out;
+
+	/* Verify that we haven't already published this pci root */
+	for (i = 0; i < root_num; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+				   str, "%x:%x", &d, &b);
+		if (err < 0)
+			goto out;
+		if (err != 2) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (d == domain && b == bus) {
+			err = 0;
+			goto out;
+		}
+	}
+
+	len = snprintf(str, sizeof(str), "root-%d", root_num);
+	if (unlikely(len >= (sizeof(str) - 1))) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	dev_dbg(&pdev->xdev->dev, "writing root %d at %04x:%02x\n",
+		root_num, domain, bus);
+
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str,
+			    "%04x:%02x", domain, bus);
+	if (err)
+		goto out;
+
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename,
+			    "root_num", "%d", (root_num + 1));
+
+out:
+	return err;
+}
+
+static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev)
+{
+	int err = 0;
+	int num_devs;
+	int domain, bus, slot, func;
+	int substate;
+	int i, len;
+	char state_str[64];
+	char dev_str[64];
+
+
+	dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n");
+
+	mutex_lock(&pdev->dev_lock);
+	/* Make sure we only reconfigure once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of devices");
+		goto out;
+	}
+
+	for (i = 0; i < num_devs; i++) {
+		len = snprintf(state_str, sizeof(state_str), "state-%d", i);
+		if (unlikely(len >= (sizeof(state_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, state_str,
+				   "%d", &substate);
+		if (err != 1)
+			substate = XenbusStateUnknown;
+
+		switch (substate) {
+		case XenbusStateInitialising:
+			dev_dbg(&pdev->xdev->dev, "Attaching dev-%d ...\n", i);
+
+			len = snprintf(dev_str, sizeof(dev_str), "dev-%d", i);
+			if (unlikely(len >= (sizeof(dev_str) - 1))) {
+				err = -ENOMEM;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "String overflow while "
+						 "reading configuration");
+				goto out;
+			}
+			err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+					   dev_str, "%x:%x:%x.%x",
+					   &domain, &bus, &slot, &func);
+			if (err < 0) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error reading device "
+						 "configuration");
+				goto out;
+			}
+			if (err != 4) {
+				err = -EINVAL;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error parsing pci device "
+						 "configuration");
+				goto out;
+			}
+
+			err = xen_pcibk_export_device(pdev, domain, bus, slot,
+						    func, i);
+			if (err)
+				goto out;
+
+			/* Publish pci roots. */
+			err = xen_pcibk_publish_pci_roots(pdev,
+						xen_pcibk_publish_pci_root);
+			if (err) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error while publish PCI root"
+						 "buses for frontend");
+				goto out;
+			}
+
+			err = xenbus_printf(XBT_NIL, pdev->xdev->nodename,
+					    state_str, "%d",
+					    XenbusStateInitialised);
+			if (err) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error switching substate of "
+						 "dev-%d\n", i);
+				goto out;
+			}
+			break;
+
+		case XenbusStateClosing:
+			dev_dbg(&pdev->xdev->dev, "Detaching dev-%d ...\n", i);
+
+			len = snprintf(dev_str, sizeof(dev_str), "vdev-%d", i);
+			if (unlikely(len >= (sizeof(dev_str) - 1))) {
+				err = -ENOMEM;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "String overflow while "
+						 "reading configuration");
+				goto out;
+			}
+			err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+					   dev_str, "%x:%x:%x.%x",
+					   &domain, &bus, &slot, &func);
+			if (err < 0) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error reading device "
+						 "configuration");
+				goto out;
+			}
+			if (err != 4) {
+				err = -EINVAL;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error parsing pci device "
+						 "configuration");
+				goto out;
+			}
+
+			err = xen_pcibk_remove_device(pdev, domain, bus, slot,
+						    func);
+			if (err)
+				goto out;
+
+			/* TODO: If at some point we implement support for pci
+			 * root hot-remove on pcifront side, we'll need to
+			 * remove unnecessary xenstore nodes of pci roots here.
+			 */
+
+			break;
+
+		default:
+			break;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfigured);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to reconfigured state!");
+		goto out;
+	}
+
+out:
+	mutex_unlock(&pdev->dev_lock);
+	return 0;
+}
+
+static void xen_pcibk_frontend_changed(struct xenbus_device *xdev,
+				     enum xenbus_state fe_state)
+{
+	struct xen_pcibk_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	dev_dbg(&xdev->dev, "fe state changed %d\n", fe_state);
+
+	switch (fe_state) {
+	case XenbusStateInitialised:
+		xen_pcibk_attach(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		xen_pcibk_reconfigure(pdev);
+		break;
+
+	case XenbusStateConnected:
+		/* pcifront switched its state from reconfiguring to connected.
+		 * Then switch to connected state.
+		 */
+		xenbus_switch_state(xdev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+		xen_pcibk_disconnect(pdev);
+		xenbus_switch_state(xdev, XenbusStateClosing);
+		break;
+
+	case XenbusStateClosed:
+		xen_pcibk_disconnect(pdev);
+		xenbus_switch_state(xdev, XenbusStateClosed);
+		if (xenbus_dev_is_online(xdev))
+			break;
+		/* fall through if not online */
+	case XenbusStateUnknown:
+		dev_dbg(&xdev->dev, "frontend is gone! unregister device\n");
+		device_unregister(&xdev->dev);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev)
+{
+	/* Get configuration from xend (if available now) */
+	int domain, bus, slot, func;
+	int err = 0;
+	int i, num_devs;
+	char dev_str[64];
+	char state_str[64];
+
+	mutex_lock(&pdev->dev_lock);
+	/* It's possible we could get the call to setup twice, so make sure
+	 * we're not already connected.
+	 */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitWait)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "getting be setup\n");
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of devices");
+		goto out;
+	}
+
+	for (i = 0; i < num_devs; i++) {
+		int l = snprintf(dev_str, sizeof(dev_str), "dev-%d", i);
+		if (unlikely(l >= (sizeof(dev_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, dev_str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err < 0) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading device configuration");
+			goto out;
+		}
+		if (err != 4) {
+			err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error parsing pci device "
+					 "configuration");
+			goto out;
+		}
+
+		err = xen_pcibk_export_device(pdev, domain, bus, slot, func, i);
+		if (err)
+			goto out;
+
+		/* Switch substate of this device. */
+		l = snprintf(state_str, sizeof(state_str), "state-%d", i);
+		if (unlikely(l >= (sizeof(state_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+		err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, state_str,
+				    "%d", XenbusStateInitialised);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err, "Error switching "
+					 "substate of dev-%d\n", i);
+			goto out;
+		}
+	}
+
+	err = xen_pcibk_publish_pci_roots(pdev, xen_pcibk_publish_pci_root);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error while publish PCI root buses "
+				 "for frontend");
+		goto out;
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+	if (err)
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to initialised state!");
+
+out:
+	mutex_unlock(&pdev->dev_lock);
+	if (!err)
+		/* see if pcifront is already configured (if not, we'll wait) */
+		xen_pcibk_attach(pdev);
+	return err;
+}
+
+static void xen_pcibk_be_watch(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len)
+{
+	struct xen_pcibk_device *pdev =
+	    container_of(watch, struct xen_pcibk_device, be_watch);
+
+	switch (xenbus_read_driver_state(pdev->xdev->nodename)) {
+	case XenbusStateInitWait:
+		xen_pcibk_setup_backend(pdev);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int xen_pcibk_xenbus_probe(struct xenbus_device *dev,
+				const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct xen_pcibk_device *pdev = alloc_pdev(dev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(dev, err,
+				 "Error allocating xen_pcibk_device struct");
+		goto out;
+	}
+
+	/* wait for xend to configure us */
+	err = xenbus_switch_state(dev, XenbusStateInitWait);
+	if (err)
+		goto out;
+
+	/* watch the backend node for backend configuration information */
+	err = xenbus_watch_path(dev, dev->nodename, &pdev->be_watch,
+				xen_pcibk_be_watch);
+	if (err)
+		goto out;
+
+	pdev->be_watching = 1;
+
+	/* We need to force a call to our callback here in case
+	 * xend already configured us!
+	 */
+	xen_pcibk_be_watch(&pdev->be_watch, NULL, 0);
+
+out:
+	return err;
+}
+
+static int xen_pcibk_xenbus_remove(struct xenbus_device *dev)
+{
+	struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev);
+
+	if (pdev != NULL)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xen_pcibk_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static DEFINE_XENBUS_DRIVER(xen_pcibk, DRV_NAME,
+	.probe			= xen_pcibk_xenbus_probe,
+	.remove			= xen_pcibk_xenbus_remove,
+	.otherend_changed	= xen_pcibk_frontend_changed,
+);
+
+const struct xen_pcibk_backend *__read_mostly xen_pcibk_backend;
+
+int __init xen_pcibk_xenbus_register(void)
+{
+	xen_pcibk_wq = create_workqueue("xen_pciback_workqueue");
+	if (!xen_pcibk_wq) {
+		printk(KERN_ERR "%s: create"
+			"xen_pciback_workqueue failed\n", __func__);
+		return -EFAULT;
+	}
+	xen_pcibk_backend = &xen_pcibk_vpci_backend;
+	if (passthrough)
+		xen_pcibk_backend = &xen_pcibk_passthrough_backend;
+	pr_info(DRV_NAME ": backend is %s\n", xen_pcibk_backend->name);
+	return xenbus_register_backend(&xen_pcibk_driver);
+}
+
+void __exit xen_pcibk_xenbus_unregister(void)
+{
+	destroy_workqueue(xen_pcibk_wq);
+	xenbus_unregister_driver(&xen_pcibk_driver);
+}
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
new file mode 100644
index 00000000..146c9489
--- /dev/null
+++ b/drivers/xen/xen-selfballoon.c
@@ -0,0 +1,545 @@
+/******************************************************************************
+ * Xen selfballoon driver (and optional frontswap self-shrinking driver)
+ *
+ * Copyright (c) 2009-2011, Dan Magenheimer, Oracle Corp.
+ *
+ * This code complements the cleancache and frontswap patchsets to optimize
+ * support for Xen Transcendent Memory ("tmem").  The policy it implements
+ * is rudimentary and will likely improve over time, but it does work well
+ * enough today.
+ *
+ * Two functionalities are implemented here which both use "control theory"
+ * (feedback) to optimize memory utilization. In a virtualized environment
+ * such as Xen, RAM is often a scarce resource and we would like to ensure
+ * that each of a possibly large number of virtual machines is using RAM
+ * efficiently, i.e. using as little as possible when under light load
+ * and obtaining as much as possible when memory demands are high.
+ * Since RAM needs vary highly dynamically and sometimes dramatically,
+ * "hysteresis" is used, that is, memory target is determined not just
+ * on current data but also on past data stored in the system.
+ *
+ * "Selfballooning" creates memory pressure by managing the Xen balloon
+ * driver to decrease and increase available kernel memory, driven
+ * largely by the target value of "Committed_AS" (see /proc/meminfo).
+ * Since Committed_AS does not account for clean mapped pages (i.e. pages
+ * in RAM that are identical to pages on disk), selfballooning has the
+ * affect of pushing less frequently used clean pagecache pages out of
+ * kernel RAM and, presumably using cleancache, into Xen tmem where
+ * Xen can more efficiently optimize RAM utilization for such pages.
+ *
+ * When kernel memory demand unexpectedly increases faster than Xen, via
+ * the selfballoon driver, is able to (or chooses to) provide usable RAM,
+ * the kernel may invoke swapping.  In most cases, frontswap is able
+ * to absorb this swapping into Xen tmem.  However, due to the fact
+ * that the kernel swap subsystem assumes swapping occurs to a disk,
+ * swapped pages may sit on the disk for a very long time; even if
+ * the kernel knows the page will never be used again.  This is because
+ * the disk space costs very little and can be overwritten when
+ * necessary.  When such stale pages are in frontswap, however, they
+ * are taking up valuable real estate.  "Frontswap selfshrinking" works
+ * to resolve this:  When frontswap activity is otherwise stable
+ * and the guest kernel is not under memory pressure, the "frontswap
+ * selfshrinking" accounts for this by providing pressure to remove some
+ * pages from frontswap and return them to kernel memory.
+ *
+ * For both "selfballooning" and "frontswap-selfshrinking", a worker
+ * thread is used and sysfs tunables are provided to adjust the frequency
+ * and rate of adjustments to achieve the goal, as well as to disable one
+ * or both functions independently.
+ *
+ * While some argue that this functionality can and should be implemented
+ * in userspace, it has been observed that bad things happen (e.g. OOMs).
+ *
+ * System configuration note: Selfballooning should not be enabled on
+ * systems without a sufficiently large swap device configured; for best
+ * results, it is recommended that total swap be increased by the size
+ * of the guest memory.  Also, while technically not required to be
+ * configured, it is highly recommended that frontswap also be configured
+ * and enabled when selfballooning is running.  So, selfballooning
+ * is disabled by default if frontswap is not configured and can only
+ * be enabled with the "selfballooning" kernel boot option; similarly
+ * selfballooning is enabled by default if frontswap is configured and
+ * can be disabled with the "noselfballooning" kernel boot option.  Finally,
+ * when frontswap is configured, frontswap-selfshrinking can be disabled
+ * with the "noselfshrink" kernel boot option.
+ *
+ * Selfballooning is disallowed in domain0 and force-disabled.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/bootmem.h>
+#include <linux/swap.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/device.h>
+#include <xen/balloon.h>
+#include <xen/tmem.h>
+#include <xen/xen.h>
+
+/* Enable/disable with sysfs. */
+static int xen_selfballooning_enabled __read_mostly;
+
+/*
+ * Controls rate at which memory target (this iteration) approaches
+ * ultimate goal when memory need is increasing (up-hysteresis) or
+ * decreasing (down-hysteresis). Higher values of hysteresis cause
+ * slower increases/decreases. The default values for the various
+ * parameters were deemed reasonable by experimentation, may be
+ * workload-dependent, and can all be adjusted via sysfs.
+ */
+static unsigned int selfballoon_downhysteresis __read_mostly = 8;
+static unsigned int selfballoon_uphysteresis __read_mostly = 1;
+
+/* In HZ, controls frequency of worker invocation. */
+static unsigned int selfballoon_interval __read_mostly = 5;
+
+/*
+ * Minimum usable RAM in MB for selfballooning target for balloon.
+ * If non-zero, it is added to totalreserve_pages and self-ballooning
+ * will not balloon below the sum.  If zero, a piecewise linear function
+ * is calculated as a minimum and added to totalreserve_pages.  Note that
+ * setting this value indiscriminately may cause OOMs and crashes.
+ */
+static unsigned int selfballoon_min_usable_mb;
+
+static void selfballoon_process(struct work_struct *work);
+static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
+
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+
+/* Enable/disable with sysfs. */
+static bool frontswap_selfshrinking __read_mostly;
+
+/* Enable/disable with kernel boot option. */
+static bool use_frontswap_selfshrink __initdata = true;
+
+/*
+ * The default values for the following parameters were deemed reasonable
+ * by experimentation, may be workload-dependent, and can all be
+ * adjusted via sysfs.
+ */
+
+/* Control rate for frontswap shrinking. Higher hysteresis is slower. */
+static unsigned int frontswap_hysteresis __read_mostly = 20;
+
+/*
+ * Number of selfballoon worker invocations to wait before observing that
+ * frontswap selfshrinking should commence. Note that selfshrinking does
+ * not use a separate worker thread.
+ */
+static unsigned int frontswap_inertia __read_mostly = 3;
+
+/* Countdown to next invocation of frontswap_shrink() */
+static unsigned long frontswap_inertia_counter;
+
+/*
+ * Invoked by the selfballoon worker thread, uses current number of pages
+ * in frontswap (frontswap_curr_pages()), previous status, and control
+ * values (hysteresis and inertia) to determine if frontswap should be
+ * shrunk and what the new frontswap size should be.  Note that
+ * frontswap_shrink is essentially a partial swapoff that immediately
+ * transfers pages from the "swap device" (frontswap) back into kernel
+ * RAM; despite the name, frontswap "shrinking" is very different from
+ * the "shrinker" interface used by the kernel MM subsystem to reclaim
+ * memory.
+ */
+static void frontswap_selfshrink(void)
+{
+	static unsigned long cur_frontswap_pages;
+	static unsigned long last_frontswap_pages;
+	static unsigned long tgt_frontswap_pages;
+
+	last_frontswap_pages = cur_frontswap_pages;
+	cur_frontswap_pages = frontswap_curr_pages();
+	if (!cur_frontswap_pages ||
+			(cur_frontswap_pages > last_frontswap_pages)) {
+		frontswap_inertia_counter = frontswap_inertia;
+		return;
+	}
+	if (frontswap_inertia_counter && --frontswap_inertia_counter)
+		return;
+	if (cur_frontswap_pages <= frontswap_hysteresis)
+		tgt_frontswap_pages = 0;
+	else
+		tgt_frontswap_pages = cur_frontswap_pages -
+			(cur_frontswap_pages / frontswap_hysteresis);
+	frontswap_shrink(tgt_frontswap_pages);
+}
+
+static int __init xen_nofrontswap_selfshrink_setup(char *s)
+{
+	use_frontswap_selfshrink = false;
+	return 1;
+}
+
+__setup("noselfshrink", xen_nofrontswap_selfshrink_setup);
+
+/* Disable with kernel boot option. */
+static bool use_selfballooning __initdata = true;
+
+static int __init xen_noselfballooning_setup(char *s)
+{
+	use_selfballooning = false;
+	return 1;
+}
+
+__setup("noselfballooning", xen_noselfballooning_setup);
+#else /* !CONFIG_FRONTSWAP */
+/* Enable with kernel boot option. */
+static bool use_selfballooning __initdata = false;
+
+static int __init xen_selfballooning_setup(char *s)
+{
+	use_selfballooning = true;
+	return 1;
+}
+
+__setup("selfballooning", xen_selfballooning_setup);
+#endif /* CONFIG_FRONTSWAP */
+
+#define MB2PAGES(mb)	((mb) << (20 - PAGE_SHIFT))
+
+/*
+ * Use current balloon size, the goal (vm_committed_as), and hysteresis
+ * parameters to set a new target balloon size
+ */
+static void selfballoon_process(struct work_struct *work)
+{
+	unsigned long cur_pages, goal_pages, tgt_pages, floor_pages;
+	unsigned long useful_pages;
+	bool reset_timer = false;
+
+	if (xen_selfballooning_enabled) {
+		cur_pages = totalram_pages;
+		tgt_pages = cur_pages; /* default is no change */
+		goal_pages = percpu_counter_read_positive(&vm_committed_as) +
+				totalreserve_pages;
+#ifdef CONFIG_FRONTSWAP
+		/* allow space for frontswap pages to be repatriated */
+		if (frontswap_selfshrinking && frontswap_enabled)
+			goal_pages += frontswap_curr_pages();
+#endif
+		if (cur_pages > goal_pages)
+			tgt_pages = cur_pages -
+				((cur_pages - goal_pages) /
+				  selfballoon_downhysteresis);
+		else if (cur_pages < goal_pages)
+			tgt_pages = cur_pages +
+				((goal_pages - cur_pages) /
+				  selfballoon_uphysteresis);
+		/* else if cur_pages == goal_pages, no change */
+		useful_pages = max_pfn - totalreserve_pages;
+		if (selfballoon_min_usable_mb != 0)
+			floor_pages = totalreserve_pages +
+					MB2PAGES(selfballoon_min_usable_mb);
+		/* piecewise linear function ending in ~3% slope */
+		else if (useful_pages < MB2PAGES(16))
+			floor_pages = max_pfn; /* not worth ballooning */
+		else if (useful_pages < MB2PAGES(64))
+			floor_pages = totalreserve_pages + MB2PAGES(16) +
+					((useful_pages - MB2PAGES(16)) >> 1);
+		else if (useful_pages < MB2PAGES(512))
+			floor_pages = totalreserve_pages + MB2PAGES(40) +
+					((useful_pages - MB2PAGES(40)) >> 3);
+		else /* useful_pages >= MB2PAGES(512) */
+			floor_pages = totalreserve_pages + MB2PAGES(99) +
+					((useful_pages - MB2PAGES(99)) >> 5);
+		if (tgt_pages < floor_pages)
+			tgt_pages = floor_pages;
+		balloon_set_new_target(tgt_pages +
+			balloon_stats.current_pages - totalram_pages);
+		reset_timer = true;
+	}
+#ifdef CONFIG_FRONTSWAP
+	if (frontswap_selfshrinking && frontswap_enabled) {
+		frontswap_selfshrink();
+		reset_timer = true;
+	}
+#endif
+	if (reset_timer)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+}
+
+#ifdef CONFIG_SYSFS
+
+#include <linux/capability.h>
+
+#define SELFBALLOON_SHOW(name, format, args...)				\
+	static ssize_t show_##name(struct device *dev,	\
+					  struct device_attribute *attr, \
+					  char *buf) \
+	{ \
+		return sprintf(buf, format, ##args); \
+	}
+
+SELFBALLOON_SHOW(selfballooning, "%d\n", xen_selfballooning_enabled);
+
+static ssize_t store_selfballooning(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf,
+			    size_t count)
+{
+	bool was_enabled = xen_selfballooning_enabled;
+	unsigned long tmp;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = strict_strtoul(buf, 10, &tmp);
+	if (err || ((tmp != 0) && (tmp != 1)))
+		return -EINVAL;
+
+	xen_selfballooning_enabled = !!tmp;
+	if (!was_enabled && xen_selfballooning_enabled)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+
+	return count;
+}
+
+static DEVICE_ATTR(selfballooning, S_IRUGO | S_IWUSR,
+		   show_selfballooning, store_selfballooning);
+
+SELFBALLOON_SHOW(selfballoon_interval, "%d\n", selfballoon_interval);
+
+static ssize_t store_selfballoon_interval(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf,
+					  size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_interval = val;
+	return count;
+}
+
+static DEVICE_ATTR(selfballoon_interval, S_IRUGO | S_IWUSR,
+		   show_selfballoon_interval, store_selfballoon_interval);
+
+SELFBALLOON_SHOW(selfballoon_downhys, "%d\n", selfballoon_downhysteresis);
+
+static ssize_t store_selfballoon_downhys(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf,
+					 size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_downhysteresis = val;
+	return count;
+}
+
+static DEVICE_ATTR(selfballoon_downhysteresis, S_IRUGO | S_IWUSR,
+		   show_selfballoon_downhys, store_selfballoon_downhys);
+
+
+SELFBALLOON_SHOW(selfballoon_uphys, "%d\n", selfballoon_uphysteresis);
+
+static ssize_t store_selfballoon_uphys(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf,
+				       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_uphysteresis = val;
+	return count;
+}
+
+static DEVICE_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
+		   show_selfballoon_uphys, store_selfballoon_uphys);
+
+SELFBALLOON_SHOW(selfballoon_min_usable_mb, "%d\n",
+				selfballoon_min_usable_mb);
+
+static ssize_t store_selfballoon_min_usable_mb(struct device *dev,
+					       struct device_attribute *attr,
+					       const char *buf,
+					       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_min_usable_mb = val;
+	return count;
+}
+
+static DEVICE_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
+		   show_selfballoon_min_usable_mb,
+		   store_selfballoon_min_usable_mb);
+
+
+#ifdef CONFIG_FRONTSWAP
+SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
+
+static ssize_t store_frontswap_selfshrinking(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf,
+					     size_t count)
+{
+	bool was_enabled = frontswap_selfshrinking;
+	unsigned long tmp;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &tmp);
+	if (err || ((tmp != 0) && (tmp != 1)))
+		return -EINVAL;
+	frontswap_selfshrinking = !!tmp;
+	if (!was_enabled && !xen_selfballooning_enabled &&
+	     frontswap_selfshrinking)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+
+	return count;
+}
+
+static DEVICE_ATTR(frontswap_selfshrinking, S_IRUGO | S_IWUSR,
+		   show_frontswap_selfshrinking, store_frontswap_selfshrinking);
+
+SELFBALLOON_SHOW(frontswap_inertia, "%d\n", frontswap_inertia);
+
+static ssize_t store_frontswap_inertia(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf,
+				       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	frontswap_inertia = val;
+	frontswap_inertia_counter = val;
+	return count;
+}
+
+static DEVICE_ATTR(frontswap_inertia, S_IRUGO | S_IWUSR,
+		   show_frontswap_inertia, store_frontswap_inertia);
+
+SELFBALLOON_SHOW(frontswap_hysteresis, "%d\n", frontswap_hysteresis);
+
+static ssize_t store_frontswap_hysteresis(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf,
+					  size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	frontswap_hysteresis = val;
+	return count;
+}
+
+static DEVICE_ATTR(frontswap_hysteresis, S_IRUGO | S_IWUSR,
+		   show_frontswap_hysteresis, store_frontswap_hysteresis);
+
+#endif /* CONFIG_FRONTSWAP */
+
+static struct attribute *selfballoon_attrs[] = {
+	&dev_attr_selfballooning.attr,
+	&dev_attr_selfballoon_interval.attr,
+	&dev_attr_selfballoon_downhysteresis.attr,
+	&dev_attr_selfballoon_uphysteresis.attr,
+	&dev_attr_selfballoon_min_usable_mb.attr,
+#ifdef CONFIG_FRONTSWAP
+	&dev_attr_frontswap_selfshrinking.attr,
+	&dev_attr_frontswap_hysteresis.attr,
+	&dev_attr_frontswap_inertia.attr,
+#endif
+	NULL
+};
+
+static const struct attribute_group selfballoon_group = {
+	.name = "selfballoon",
+	.attrs = selfballoon_attrs
+};
+#endif
+
+int register_xen_selfballooning(struct device *dev)
+{
+	int error = -1;
+
+#ifdef CONFIG_SYSFS
+	error = sysfs_create_group(&dev->kobj, &selfballoon_group);
+#endif
+	return error;
+}
+EXPORT_SYMBOL(register_xen_selfballooning);
+
+static int __init xen_selfballoon_init(void)
+{
+	bool enable = false;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (xen_initial_domain()) {
+		pr_info("xen/balloon: Xen selfballooning driver "
+				"disabled for domain0.\n");
+		return -ENODEV;
+	}
+
+	xen_selfballooning_enabled = tmem_enabled && use_selfballooning;
+	if (xen_selfballooning_enabled) {
+		pr_info("xen/balloon: Initializing Xen "
+					"selfballooning driver.\n");
+		enable = true;
+	}
+#ifdef CONFIG_FRONTSWAP
+	frontswap_selfshrinking = tmem_enabled && use_frontswap_selfshrink;
+	if (frontswap_selfshrinking) {
+		pr_info("xen/balloon: Initializing frontswap "
+					"selfshrinking driver.\n");
+		enable = true;
+	}
+#endif
+	if (!enable)
+		return -ENODEV;
+
+	schedule_delayed_work(&selfballoon_worker, selfballoon_interval * HZ);
+
+	return 0;
+}
+
+subsys_initcall(xen_selfballoon_init);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/xenbus/Makefile b/drivers/xen/xenbus/Makefile
new file mode 100644
index 00000000..31e2e905
--- /dev/null
+++ b/drivers/xen/xenbus/Makefile
@@ -0,0 +1,14 @@
+obj-y	+= xenbus.o
+obj-y	+= xenbus_dev_frontend.o
+
+xenbus-objs =
+xenbus-objs += xenbus_client.o
+xenbus-objs += xenbus_comms.o
+xenbus-objs += xenbus_xs.o
+xenbus-objs += xenbus_probe.o
+
+xenbus-be-objs-$(CONFIG_XEN_BACKEND) += xenbus_probe_backend.o
+xenbus-objs += $(xenbus-be-objs-y)
+
+obj-$(CONFIG_XEN_BACKEND) += xenbus_dev_backend.o
+obj-$(CONFIG_XEN_XENBUS_FRONTEND) += xenbus_probe_frontend.o
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
new file mode 100644
index 00000000..b3e146ed
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -0,0 +1,750 @@
+/******************************************************************************
+ * Client-facing interface for the Xenbus driver.  In other words, the
+ * interface between the Xenbus and the device-specific code, be it the
+ * frontend or the backend of that driver.
+ *
+ * Copyright (C) 2005 XenSource Ltd
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/export.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/page.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/event_channel.h>
+#include <xen/balloon.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/xen.h>
+
+#include "xenbus_probe.h"
+
+struct xenbus_map_node {
+	struct list_head next;
+	union {
+		struct vm_struct *area; /* PV */
+		struct page *page;     /* HVM */
+	};
+	grant_handle_t handle;
+};
+
+static DEFINE_SPINLOCK(xenbus_valloc_lock);
+static LIST_HEAD(xenbus_valloc_pages);
+
+struct xenbus_ring_ops {
+	int (*map)(struct xenbus_device *dev, int gnt, void **vaddr);
+	int (*unmap)(struct xenbus_device *dev, void *vaddr);
+};
+
+static const struct xenbus_ring_ops *ring_ops __read_mostly;
+
+const char *xenbus_strstate(enum xenbus_state state)
+{
+	static const char *const name[] = {
+		[ XenbusStateUnknown      ] = "Unknown",
+		[ XenbusStateInitialising ] = "Initialising",
+		[ XenbusStateInitWait     ] = "InitWait",
+		[ XenbusStateInitialised  ] = "Initialised",
+		[ XenbusStateConnected    ] = "Connected",
+		[ XenbusStateClosing      ] = "Closing",
+		[ XenbusStateClosed	  ] = "Closed",
+		[XenbusStateReconfiguring] = "Reconfiguring",
+		[XenbusStateReconfigured] = "Reconfigured",
+	};
+	return (state < ARRAY_SIZE(name)) ? name[state] : "INVALID";
+}
+EXPORT_SYMBOL_GPL(xenbus_strstate);
+
+/**
+ * xenbus_watch_path - register a watch
+ * @dev: xenbus device
+ * @path: path to watch
+ * @watch: watch to register
+ * @callback: callback to register
+ *
+ * Register a @watch on the given path, using the given xenbus_watch structure
+ * for storage, and the given @callback function as the callback.  Return 0 on
+ * success, or -errno on error.  On success, the given @path will be saved as
+ * @watch->node, and remains the caller's to free.  On error, @watch->node will
+ * be NULL, the device will switch to %XenbusStateClosing, and the error will
+ * be saved in the store.
+ */
+int xenbus_watch_path(struct xenbus_device *dev, const char *path,
+		      struct xenbus_watch *watch,
+		      void (*callback)(struct xenbus_watch *,
+				       const char **, unsigned int))
+{
+	int err;
+
+	watch->node = path;
+	watch->callback = callback;
+
+	err = register_xenbus_watch(watch);
+
+	if (err) {
+		watch->node = NULL;
+		watch->callback = NULL;
+		xenbus_dev_fatal(dev, err, "adding watch on %s", path);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_watch_path);
+
+
+/**
+ * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path
+ * @dev: xenbus device
+ * @watch: watch to register
+ * @callback: callback to register
+ * @pathfmt: format of path to watch
+ *
+ * Register a watch on the given @path, using the given xenbus_watch
+ * structure for storage, and the given @callback function as the callback.
+ * Return 0 on success, or -errno on error.  On success, the watched path
+ * (@path/@path2) will be saved as @watch->node, and becomes the caller's to
+ * kfree().  On error, watch->node will be NULL, so the caller has nothing to
+ * free, the device will switch to %XenbusStateClosing, and the error will be
+ * saved in the store.
+ */
+int xenbus_watch_pathfmt(struct xenbus_device *dev,
+			 struct xenbus_watch *watch,
+			 void (*callback)(struct xenbus_watch *,
+					const char **, unsigned int),
+			 const char *pathfmt, ...)
+{
+	int err;
+	va_list ap;
+	char *path;
+
+	va_start(ap, pathfmt);
+	path = kvasprintf(GFP_NOIO | __GFP_HIGH, pathfmt, ap);
+	va_end(ap);
+
+	if (!path) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating path for watch");
+		return -ENOMEM;
+	}
+	err = xenbus_watch_path(dev, path, watch, callback);
+
+	if (err)
+		kfree(path);
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_watch_pathfmt);
+
+static void xenbus_switch_fatal(struct xenbus_device *, int, int,
+				const char *, ...);
+
+static int
+__xenbus_switch_state(struct xenbus_device *dev,
+		      enum xenbus_state state, int depth)
+{
+	/* We check whether the state is currently set to the given value, and
+	   if not, then the state is set.  We don't want to unconditionally
+	   write the given state, because we don't want to fire watches
+	   unnecessarily.  Furthermore, if the node has gone, we don't write
+	   to it, as the device will be tearing down, and we don't want to
+	   resurrect that directory.
+
+	   Note that, because of this cached value of our state, this
+	   function will not take a caller's Xenstore transaction
+	   (something it was trying to in the past) because dev->state
+	   would not get reset if the transaction was aborted.
+	 */
+
+	struct xenbus_transaction xbt;
+	int current_state;
+	int err, abort;
+
+	if (state == dev->state)
+		return 0;
+
+again:
+	abort = 1;
+
+	err = xenbus_transaction_start(&xbt);
+	if (err) {
+		xenbus_switch_fatal(dev, depth, err, "starting transaction");
+		return 0;
+	}
+
+	err = xenbus_scanf(xbt, dev->nodename, "state", "%d", &current_state);
+	if (err != 1)
+		goto abort;
+
+	err = xenbus_printf(xbt, dev->nodename, "state", "%d", state);
+	if (err) {
+		xenbus_switch_fatal(dev, depth, err, "writing new state");
+		goto abort;
+	}
+
+	abort = 0;
+abort:
+	err = xenbus_transaction_end(xbt, abort);
+	if (err) {
+		if (err == -EAGAIN && !abort)
+			goto again;
+		xenbus_switch_fatal(dev, depth, err, "ending transaction");
+	} else
+		dev->state = state;
+
+	return 0;
+}
+
+/**
+ * xenbus_switch_state
+ * @dev: xenbus device
+ * @state: new state
+ *
+ * Advertise in the store a change of the given driver to the given new_state.
+ * Return 0 on success, or -errno on error.  On error, the device will switch
+ * to XenbusStateClosing, and the error will be saved in the store.
+ */
+int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
+{
+	return __xenbus_switch_state(dev, state, 0);
+}
+
+EXPORT_SYMBOL_GPL(xenbus_switch_state);
+
+int xenbus_frontend_closed(struct xenbus_device *dev)
+{
+	xenbus_switch_state(dev, XenbusStateClosed);
+	complete(&dev->down);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_frontend_closed);
+
+/**
+ * Return the path to the error node for the given device, or NULL on failure.
+ * If the value returned is non-NULL, then it is the caller's to kfree.
+ */
+static char *error_path(struct xenbus_device *dev)
+{
+	return kasprintf(GFP_KERNEL, "error/%s", dev->nodename);
+}
+
+
+static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
+				const char *fmt, va_list ap)
+{
+	int ret;
+	unsigned int len;
+	char *printf_buffer = NULL;
+	char *path_buffer = NULL;
+
+#define PRINTF_BUFFER_SIZE 4096
+	printf_buffer = kmalloc(PRINTF_BUFFER_SIZE, GFP_KERNEL);
+	if (printf_buffer == NULL)
+		goto fail;
+
+	len = sprintf(printf_buffer, "%i ", -err);
+	ret = vsnprintf(printf_buffer+len, PRINTF_BUFFER_SIZE-len, fmt, ap);
+
+	BUG_ON(len + ret > PRINTF_BUFFER_SIZE-1);
+
+	dev_err(&dev->dev, "%s\n", printf_buffer);
+
+	path_buffer = error_path(dev);
+
+	if (path_buffer == NULL) {
+		dev_err(&dev->dev, "failed to write error node for %s (%s)\n",
+		       dev->nodename, printf_buffer);
+		goto fail;
+	}
+
+	if (xenbus_write(XBT_NIL, path_buffer, "error", printf_buffer) != 0) {
+		dev_err(&dev->dev, "failed to write error node for %s (%s)\n",
+		       dev->nodename, printf_buffer);
+		goto fail;
+	}
+
+fail:
+	kfree(printf_buffer);
+	kfree(path_buffer);
+}
+
+
+/**
+ * xenbus_dev_error
+ * @dev: xenbus device
+ * @err: error to report
+ * @fmt: error message format
+ *
+ * Report the given negative errno into the store, along with the given
+ * formatted message.
+ */
+void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	xenbus_va_dev_error(dev, err, fmt, ap);
+	va_end(ap);
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_error);
+
+/**
+ * xenbus_dev_fatal
+ * @dev: xenbus device
+ * @err: error to report
+ * @fmt: error message format
+ *
+ * Equivalent to xenbus_dev_error(dev, err, fmt, args), followed by
+ * xenbus_switch_state(dev, XenbusStateClosing) to schedule an orderly
+ * closedown of this driver and its peer.
+ */
+
+void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	xenbus_va_dev_error(dev, err, fmt, ap);
+	va_end(ap);
+
+	xenbus_switch_state(dev, XenbusStateClosing);
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_fatal);
+
+/**
+ * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
+ * avoiding recursion within xenbus_switch_state.
+ */
+static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err,
+				const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	xenbus_va_dev_error(dev, err, fmt, ap);
+	va_end(ap);
+
+	if (!depth)
+		__xenbus_switch_state(dev, XenbusStateClosing, 1);
+}
+
+/**
+ * xenbus_grant_ring
+ * @dev: xenbus device
+ * @ring_mfn: mfn of ring to grant
+
+ * Grant access to the given @ring_mfn to the peer of the given device.  Return
+ * 0 on success, or -errno on error.  On error, the device will switch to
+ * XenbusStateClosing, and the error will be saved in the store.
+ */
+int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn)
+{
+	int err = gnttab_grant_foreign_access(dev->otherend_id, ring_mfn, 0);
+	if (err < 0)
+		xenbus_dev_fatal(dev, err, "granting access to ring page");
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_grant_ring);
+
+
+/**
+ * Allocate an event channel for the given xenbus_device, assigning the newly
+ * created local port to *port.  Return 0 on success, or -errno on error.  On
+ * error, the device will switch to XenbusStateClosing, and the error will be
+ * saved in the store.
+ */
+int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port)
+{
+	struct evtchn_alloc_unbound alloc_unbound;
+	int err;
+
+	alloc_unbound.dom = DOMID_SELF;
+	alloc_unbound.remote_dom = dev->otherend_id;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+					  &alloc_unbound);
+	if (err)
+		xenbus_dev_fatal(dev, err, "allocating event channel");
+	else
+		*port = alloc_unbound.port;
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn);
+
+
+/**
+ * Bind to an existing interdomain event channel in another domain. Returns 0
+ * on success and stores the local port in *port. On error, returns -errno,
+ * switches the device to XenbusStateClosing, and saves the error in XenStore.
+ */
+int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port)
+{
+	struct evtchn_bind_interdomain bind_interdomain;
+	int err;
+
+	bind_interdomain.remote_dom = dev->otherend_id;
+	bind_interdomain.remote_port = remote_port;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+					  &bind_interdomain);
+	if (err)
+		xenbus_dev_fatal(dev, err,
+				 "binding to event channel %d from domain %d",
+				 remote_port, dev->otherend_id);
+	else
+		*port = bind_interdomain.local_port;
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_bind_evtchn);
+
+
+/**
+ * Free an existing event channel. Returns 0 on success or -errno on error.
+ */
+int xenbus_free_evtchn(struct xenbus_device *dev, int port)
+{
+	struct evtchn_close close;
+	int err;
+
+	close.port = port;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_close, &close);
+	if (err)
+		xenbus_dev_error(dev, err, "freeing event channel %d", port);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
+
+
+/**
+ * xenbus_map_ring_valloc
+ * @dev: xenbus device
+ * @gnt_ref: grant reference
+ * @vaddr: pointer to address to be filled out by mapping
+ *
+ * Based on Rusty Russell's skeleton driver's map_page.
+ * Map a page of memory into this domain from another domain's grant table.
+ * xenbus_map_ring_valloc allocates a page of virtual address space, maps the
+ * page to that address, and sets *vaddr to that address.
+ * Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h)
+ * or -ENOMEM on error. If an error is returned, device will switch to
+ * XenbusStateClosing and the error message will be saved in XenStore.
+ */
+int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
+{
+	return ring_ops->map(dev, gnt_ref, vaddr);
+}
+EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc);
+
+static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
+				     int gnt_ref, void **vaddr)
+{
+	struct gnttab_map_grant_ref op = {
+		.flags = GNTMAP_host_map | GNTMAP_contains_pte,
+		.ref   = gnt_ref,
+		.dom   = dev->otherend_id,
+	};
+	struct xenbus_map_node *node;
+	struct vm_struct *area;
+	pte_t *pte;
+
+	*vaddr = NULL;
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	area = alloc_vm_area(PAGE_SIZE, &pte);
+	if (!area) {
+		kfree(node);
+		return -ENOMEM;
+	}
+
+	op.host_addr = arbitrary_virt_to_machine(pte).maddr;
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status != GNTST_okay) {
+		free_vm_area(area);
+		kfree(node);
+		xenbus_dev_fatal(dev, op.status,
+				 "mapping in shared page %d from domain %d",
+				 gnt_ref, dev->otherend_id);
+		return op.status;
+	}
+
+	node->handle = op.handle;
+	node->area = area;
+
+	spin_lock(&xenbus_valloc_lock);
+	list_add(&node->next, &xenbus_valloc_pages);
+	spin_unlock(&xenbus_valloc_lock);
+
+	*vaddr = area->addr;
+	return 0;
+}
+
+static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev,
+				      int gnt_ref, void **vaddr)
+{
+	struct xenbus_map_node *node;
+	int err;
+	void *addr;
+
+	*vaddr = NULL;
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	err = alloc_xenballooned_pages(1, &node->page, false /* lowmem */);
+	if (err)
+		goto out_err;
+
+	addr = pfn_to_kaddr(page_to_pfn(node->page));
+
+	err = xenbus_map_ring(dev, gnt_ref, &node->handle, addr);
+	if (err)
+		goto out_err;
+
+	spin_lock(&xenbus_valloc_lock);
+	list_add(&node->next, &xenbus_valloc_pages);
+	spin_unlock(&xenbus_valloc_lock);
+
+	*vaddr = addr;
+	return 0;
+
+ out_err:
+	free_xenballooned_pages(1, &node->page);
+	kfree(node);
+	return err;
+}
+
+
+/**
+ * xenbus_map_ring
+ * @dev: xenbus device
+ * @gnt_ref: grant reference
+ * @handle: pointer to grant handle to be filled
+ * @vaddr: address to be mapped to
+ *
+ * Map a page of memory into this domain from another domain's grant table.
+ * xenbus_map_ring does not allocate the virtual address space (you must do
+ * this yourself!). It only maps in the page to the specified address.
+ * Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h)
+ * or -ENOMEM on error. If an error is returned, device will switch to
+ * XenbusStateClosing and the error message will be saved in XenStore.
+ */
+int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref,
+		    grant_handle_t *handle, void *vaddr)
+{
+	struct gnttab_map_grant_ref op;
+
+	gnttab_set_map_op(&op, (unsigned long)vaddr, GNTMAP_host_map, gnt_ref,
+			  dev->otherend_id);
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status != GNTST_okay) {
+		xenbus_dev_fatal(dev, op.status,
+				 "mapping in shared page %d from domain %d",
+				 gnt_ref, dev->otherend_id);
+	} else
+		*handle = op.handle;
+
+	return op.status;
+}
+EXPORT_SYMBOL_GPL(xenbus_map_ring);
+
+
+/**
+ * xenbus_unmap_ring_vfree
+ * @dev: xenbus device
+ * @vaddr: addr to unmap
+ *
+ * Based on Rusty Russell's skeleton driver's unmap_page.
+ * Unmap a page of memory in this domain that was imported from another domain.
+ * Use xenbus_unmap_ring_vfree if you mapped in your memory with
+ * xenbus_map_ring_valloc (it will free the virtual address space).
+ * Returns 0 on success and returns GNTST_* on error
+ * (see xen/include/interface/grant_table.h).
+ */
+int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
+{
+	return ring_ops->unmap(dev, vaddr);
+}
+EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);
+
+static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
+{
+	struct xenbus_map_node *node;
+	struct gnttab_unmap_grant_ref op = {
+		.host_addr = (unsigned long)vaddr,
+	};
+	unsigned int level;
+
+	spin_lock(&xenbus_valloc_lock);
+	list_for_each_entry(node, &xenbus_valloc_pages, next) {
+		if (node->area->addr == vaddr) {
+			list_del(&node->next);
+			goto found;
+		}
+	}
+	node = NULL;
+ found:
+	spin_unlock(&xenbus_valloc_lock);
+
+	if (!node) {
+		xenbus_dev_error(dev, -ENOENT,
+				 "can't find mapped virtual address %p", vaddr);
+		return GNTST_bad_virt_addr;
+	}
+
+	op.handle = node->handle;
+	op.host_addr = arbitrary_virt_to_machine(
+		lookup_address((unsigned long)vaddr, &level)).maddr;
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status == GNTST_okay)
+		free_vm_area(node->area);
+	else
+		xenbus_dev_error(dev, op.status,
+				 "unmapping page at handle %d error %d",
+				 node->handle, op.status);
+
+	kfree(node);
+	return op.status;
+}
+
+static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr)
+{
+	int rv;
+	struct xenbus_map_node *node;
+	void *addr;
+
+	spin_lock(&xenbus_valloc_lock);
+	list_for_each_entry(node, &xenbus_valloc_pages, next) {
+		addr = pfn_to_kaddr(page_to_pfn(node->page));
+		if (addr == vaddr) {
+			list_del(&node->next);
+			goto found;
+		}
+	}
+	node = addr = NULL;
+ found:
+	spin_unlock(&xenbus_valloc_lock);
+
+	if (!node) {
+		xenbus_dev_error(dev, -ENOENT,
+				 "can't find mapped virtual address %p", vaddr);
+		return GNTST_bad_virt_addr;
+	}
+
+	rv = xenbus_unmap_ring(dev, node->handle, addr);
+
+	if (!rv)
+		free_xenballooned_pages(1, &node->page);
+	else
+		WARN(1, "Leaking %p\n", vaddr);
+
+	kfree(node);
+	return rv;
+}
+
+/**
+ * xenbus_unmap_ring
+ * @dev: xenbus device
+ * @handle: grant handle
+ * @vaddr: addr to unmap
+ *
+ * Unmap a page of memory in this domain that was imported from another domain.
+ * Returns 0 on success and returns GNTST_* on error
+ * (see xen/include/interface/grant_table.h).
+ */
+int xenbus_unmap_ring(struct xenbus_device *dev,
+		      grant_handle_t handle, void *vaddr)
+{
+	struct gnttab_unmap_grant_ref op;
+
+	gnttab_set_unmap_op(&op, (unsigned long)vaddr, GNTMAP_host_map, handle);
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status != GNTST_okay)
+		xenbus_dev_error(dev, op.status,
+				 "unmapping page at handle %d error %d",
+				 handle, op.status);
+
+	return op.status;
+}
+EXPORT_SYMBOL_GPL(xenbus_unmap_ring);
+
+
+/**
+ * xenbus_read_driver_state
+ * @path: path for driver
+ *
+ * Return the state of the driver rooted at the given store path, or
+ * XenbusStateUnknown if no state can be read.
+ */
+enum xenbus_state xenbus_read_driver_state(const char *path)
+{
+	enum xenbus_state result;
+	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
+	if (err)
+		result = XenbusStateUnknown;
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(xenbus_read_driver_state);
+
+static const struct xenbus_ring_ops ring_ops_pv = {
+	.map = xenbus_map_ring_valloc_pv,
+	.unmap = xenbus_unmap_ring_vfree_pv,
+};
+
+static const struct xenbus_ring_ops ring_ops_hvm = {
+	.map = xenbus_map_ring_valloc_hvm,
+	.unmap = xenbus_unmap_ring_vfree_hvm,
+};
+
+void __init xenbus_ring_ops_init(void)
+{
+	if (xen_pv_domain())
+		ring_ops = &ring_ops_pv;
+	else
+		ring_ops = &ring_ops_hvm;
+}
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
new file mode 100644
index 00000000..2eff7a6a
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -0,0 +1,236 @@
+/******************************************************************************
+ * xenbus_comms.c
+ *
+ * Low level code to talks to Xen Store: ringbuffer and event channel.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/wait.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <xen/xenbus.h>
+#include <asm/xen/hypervisor.h>
+#include <xen/events.h>
+#include <xen/page.h>
+#include "xenbus_comms.h"
+
+static int xenbus_irq;
+
+static DECLARE_WORK(probe_work, xenbus_probe);
+
+static DECLARE_WAIT_QUEUE_HEAD(xb_waitq);
+
+static irqreturn_t wake_waiting(int irq, void *unused)
+{
+	if (unlikely(xenstored_ready == 0)) {
+		xenstored_ready = 1;
+		schedule_work(&probe_work);
+	}
+
+	wake_up(&xb_waitq);
+	return IRQ_HANDLED;
+}
+
+static int check_indexes(XENSTORE_RING_IDX cons, XENSTORE_RING_IDX prod)
+{
+	return ((prod - cons) <= XENSTORE_RING_SIZE);
+}
+
+static void *get_output_chunk(XENSTORE_RING_IDX cons,
+			      XENSTORE_RING_IDX prod,
+			      char *buf, uint32_t *len)
+{
+	*len = XENSTORE_RING_SIZE - MASK_XENSTORE_IDX(prod);
+	if ((XENSTORE_RING_SIZE - (prod - cons)) < *len)
+		*len = XENSTORE_RING_SIZE - (prod - cons);
+	return buf + MASK_XENSTORE_IDX(prod);
+}
+
+static const void *get_input_chunk(XENSTORE_RING_IDX cons,
+				   XENSTORE_RING_IDX prod,
+				   const char *buf, uint32_t *len)
+{
+	*len = XENSTORE_RING_SIZE - MASK_XENSTORE_IDX(cons);
+	if ((prod - cons) < *len)
+		*len = prod - cons;
+	return buf + MASK_XENSTORE_IDX(cons);
+}
+
+/**
+ * xb_write - low level write
+ * @data: buffer to send
+ * @len: length of buffer
+ *
+ * Returns 0 on success, error otherwise.
+ */
+int xb_write(const void *data, unsigned len)
+{
+	struct xenstore_domain_interface *intf = xen_store_interface;
+	XENSTORE_RING_IDX cons, prod;
+	int rc;
+
+	while (len != 0) {
+		void *dst;
+		unsigned int avail;
+
+		rc = wait_event_interruptible(
+			xb_waitq,
+			(intf->req_prod - intf->req_cons) !=
+			XENSTORE_RING_SIZE);
+		if (rc < 0)
+			return rc;
+
+		/* Read indexes, then verify. */
+		cons = intf->req_cons;
+		prod = intf->req_prod;
+		if (!check_indexes(cons, prod)) {
+			intf->req_cons = intf->req_prod = 0;
+			return -EIO;
+		}
+
+		dst = get_output_chunk(cons, prod, intf->req, &avail);
+		if (avail == 0)
+			continue;
+		if (avail > len)
+			avail = len;
+
+		/* Must write data /after/ reading the consumer index. */
+		mb();
+
+		memcpy(dst, data, avail);
+		data += avail;
+		len -= avail;
+
+		/* Other side must not see new producer until data is there. */
+		wmb();
+		intf->req_prod += avail;
+
+		/* Implies mb(): other side will see the updated producer. */
+		notify_remote_via_evtchn(xen_store_evtchn);
+	}
+
+	return 0;
+}
+
+int xb_data_to_read(void)
+{
+	struct xenstore_domain_interface *intf = xen_store_interface;
+	return (intf->rsp_cons != intf->rsp_prod);
+}
+
+int xb_wait_for_data_to_read(void)
+{
+	return wait_event_interruptible(xb_waitq, xb_data_to_read());
+}
+
+int xb_read(void *data, unsigned len)
+{
+	struct xenstore_domain_interface *intf = xen_store_interface;
+	XENSTORE_RING_IDX cons, prod;
+	int rc;
+
+	while (len != 0) {
+		unsigned int avail;
+		const char *src;
+
+		rc = xb_wait_for_data_to_read();
+		if (rc < 0)
+			return rc;
+
+		/* Read indexes, then verify. */
+		cons = intf->rsp_cons;
+		prod = intf->rsp_prod;
+		if (!check_indexes(cons, prod)) {
+			intf->rsp_cons = intf->rsp_prod = 0;
+			return -EIO;
+		}
+
+		src = get_input_chunk(cons, prod, intf->rsp, &avail);
+		if (avail == 0)
+			continue;
+		if (avail > len)
+			avail = len;
+
+		/* Must read data /after/ reading the producer index. */
+		rmb();
+
+		memcpy(data, src, avail);
+		data += avail;
+		len -= avail;
+
+		/* Other side must not see free space until we've copied out */
+		mb();
+		intf->rsp_cons += avail;
+
+		pr_debug("Finished read of %i bytes (%i to go)\n", avail, len);
+
+		/* Implies mb(): other side will see the updated consumer. */
+		notify_remote_via_evtchn(xen_store_evtchn);
+	}
+
+	return 0;
+}
+
+/**
+ * xb_init_comms - Set up interrupt handler off store event channel.
+ */
+int xb_init_comms(void)
+{
+	struct xenstore_domain_interface *intf = xen_store_interface;
+
+	if (intf->req_prod != intf->req_cons)
+		printk(KERN_ERR "XENBUS request ring is not quiescent "
+		       "(%08x:%08x)!\n", intf->req_cons, intf->req_prod);
+
+	if (intf->rsp_prod != intf->rsp_cons) {
+		printk(KERN_WARNING "XENBUS response ring is not quiescent "
+		       "(%08x:%08x): fixing up\n",
+		       intf->rsp_cons, intf->rsp_prod);
+		/* breaks kdump */
+		if (!reset_devices)
+			intf->rsp_cons = intf->rsp_prod;
+	}
+
+	if (xenbus_irq) {
+		/* Already have an irq; assume we're resuming */
+		rebind_evtchn_irq(xen_store_evtchn, xenbus_irq);
+	} else {
+		int err;
+		err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting,
+						0, "xenbus", &xb_waitq);
+		if (err <= 0) {
+			printk(KERN_ERR "XENBUS request irq failed %i\n", err);
+			return err;
+		}
+
+		xenbus_irq = err;
+	}
+
+	return 0;
+}
diff --git a/drivers/xen/xenbus/xenbus_comms.h b/drivers/xen/xenbus/xenbus_comms.h
new file mode 100644
index 00000000..6e42800f
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_comms.h
@@ -0,0 +1,50 @@
+/*
+ * Private include for xenbus communications.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _XENBUS_COMMS_H
+#define _XENBUS_COMMS_H
+
+#include <linux/fs.h>
+
+int xs_init(void);
+int xb_init_comms(void);
+
+/* Low level routines. */
+int xb_write(const void *data, unsigned len);
+int xb_read(void *data, unsigned len);
+int xb_data_to_read(void);
+int xb_wait_for_data_to_read(void);
+int xs_input_avail(void);
+extern struct xenstore_domain_interface *xen_store_interface;
+extern int xen_store_evtchn;
+
+extern const struct file_operations xen_xenbus_fops;
+
+#endif /* _XENBUS_COMMS_H */
diff --git a/drivers/xen/xenbus/xenbus_dev_backend.c b/drivers/xen/xenbus/xenbus_dev_backend.c
new file mode 100644
index 00000000..3d3be78c
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_dev_backend.c
@@ -0,0 +1,90 @@
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/capability.h>
+
+#include <xen/xen.h>
+#include <xen/page.h>
+#include <xen/xenbus_dev.h>
+
+#include "xenbus_comms.h"
+
+MODULE_LICENSE("GPL");
+
+static int xenbus_backend_open(struct inode *inode, struct file *filp)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return nonseekable_open(inode, filp);
+}
+
+static long xenbus_backend_ioctl(struct file *file, unsigned int cmd, unsigned long data)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+		case IOCTL_XENBUS_BACKEND_EVTCHN:
+			if (xen_store_evtchn > 0)
+				return xen_store_evtchn;
+			return -ENODEV;
+
+		default:
+			return -ENOTTY;
+	}
+}
+
+static int xenbus_backend_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if ((size > PAGE_SIZE) || (vma->vm_pgoff != 0))
+		return -EINVAL;
+
+	if (remap_pfn_range(vma, vma->vm_start,
+			    virt_to_pfn(xen_store_interface),
+			    size, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+const struct file_operations xenbus_backend_fops = {
+	.open = xenbus_backend_open,
+	.mmap = xenbus_backend_mmap,
+	.unlocked_ioctl = xenbus_backend_ioctl,
+};
+
+static struct miscdevice xenbus_backend_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "xen/xenbus_backend",
+	.fops = &xenbus_backend_fops,
+};
+
+static int __init xenbus_backend_init(void)
+{
+	int err;
+
+	if (!xen_initial_domain())
+		return -ENODEV;
+
+	err = misc_register(&xenbus_backend_dev);
+	if (err)
+		printk(KERN_ERR "Could not register xenbus backend device\n");
+	return err;
+}
+
+static void __exit xenbus_backend_exit(void)
+{
+	misc_deregister(&xenbus_backend_dev);
+}
+
+module_init(xenbus_backend_init);
+module_exit(xenbus_backend_exit);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
new file mode 100644
index 00000000..89f76252
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -0,0 +1,629 @@
+/*
+ * Driver giving user-space access to the kernel's xenbus connection
+ * to xenstore.
+ *
+ * Copyright (c) 2005, Christian Limpach
+ * Copyright (c) 2005, Rusty Russell, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Changes:
+ * 2008-10-07  Alex Zeffertt    Replaced /proc/xen/xenbus with xenfs filesystem
+ *                              and /proc/xen compatibility mount point.
+ *                              Turned xenfs into a loadable module.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/uio.h>
+#include <linux/notifier.h>
+#include <linux/wait.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+
+#include "xenbus_comms.h"
+
+#include <xen/xenbus.h>
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
+MODULE_LICENSE("GPL");
+
+/*
+ * An element of a list of outstanding transactions, for which we're
+ * still waiting a reply.
+ */
+struct xenbus_transaction_holder {
+	struct list_head list;
+	struct xenbus_transaction handle;
+};
+
+/*
+ * A buffer of data on the queue.
+ */
+struct read_buffer {
+	struct list_head list;
+	unsigned int cons;
+	unsigned int len;
+	char msg[];
+};
+
+struct xenbus_file_priv {
+	/*
+	 * msgbuffer_mutex is held while partial requests are built up
+	 * and complete requests are acted on.  It therefore protects
+	 * the "transactions" and "watches" lists, and the partial
+	 * request length and buffer.
+	 *
+	 * reply_mutex protects the reply being built up to return to
+	 * usermode.  It nests inside msgbuffer_mutex but may be held
+	 * alone during a watch callback.
+	 */
+	struct mutex msgbuffer_mutex;
+
+	/* In-progress transactions */
+	struct list_head transactions;
+
+	/* Active watches. */
+	struct list_head watches;
+
+	/* Partial request. */
+	unsigned int len;
+	union {
+		struct xsd_sockmsg msg;
+		char buffer[XENSTORE_PAYLOAD_MAX];
+	} u;
+
+	/* Response queue. */
+	struct mutex reply_mutex;
+	struct list_head read_buffers;
+	wait_queue_head_t read_waitq;
+
+};
+
+/* Read out any raw xenbus messages queued up. */
+static ssize_t xenbus_file_read(struct file *filp,
+			       char __user *ubuf,
+			       size_t len, loff_t *ppos)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+	struct read_buffer *rb;
+	unsigned i;
+	int ret;
+
+	mutex_lock(&u->reply_mutex);
+again:
+	while (list_empty(&u->read_buffers)) {
+		mutex_unlock(&u->reply_mutex);
+		if (filp->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		ret = wait_event_interruptible(u->read_waitq,
+					       !list_empty(&u->read_buffers));
+		if (ret)
+			return ret;
+		mutex_lock(&u->reply_mutex);
+	}
+
+	rb = list_entry(u->read_buffers.next, struct read_buffer, list);
+	i = 0;
+	while (i < len) {
+		unsigned sz = min((unsigned)len - i, rb->len - rb->cons);
+
+		ret = copy_to_user(ubuf + i, &rb->msg[rb->cons], sz);
+
+		i += sz - ret;
+		rb->cons += sz - ret;
+
+		if (ret != 0) {
+			if (i == 0)
+				i = -EFAULT;
+			goto out;
+		}
+
+		/* Clear out buffer if it has been consumed */
+		if (rb->cons == rb->len) {
+			list_del(&rb->list);
+			kfree(rb);
+			if (list_empty(&u->read_buffers))
+				break;
+			rb = list_entry(u->read_buffers.next,
+					struct read_buffer, list);
+		}
+	}
+	if (i == 0)
+		goto again;
+
+out:
+	mutex_unlock(&u->reply_mutex);
+	return i;
+}
+
+/*
+ * Add a buffer to the queue.  Caller must hold the appropriate lock
+ * if the queue is not local.  (Commonly the caller will build up
+ * multiple queued buffers on a temporary local list, and then add it
+ * to the appropriate list under lock once all the buffers have een
+ * successfully allocated.)
+ */
+static int queue_reply(struct list_head *queue, const void *data, size_t len)
+{
+	struct read_buffer *rb;
+
+	if (len == 0)
+		return 0;
+
+	rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL);
+	if (rb == NULL)
+		return -ENOMEM;
+
+	rb->cons = 0;
+	rb->len = len;
+
+	memcpy(rb->msg, data, len);
+
+	list_add_tail(&rb->list, queue);
+	return 0;
+}
+
+/*
+ * Free all the read_buffer s on a list.
+ * Caller must have sole reference to list.
+ */
+static void queue_cleanup(struct list_head *list)
+{
+	struct read_buffer *rb;
+
+	while (!list_empty(list)) {
+		rb = list_entry(list->next, struct read_buffer, list);
+		list_del(list->next);
+		kfree(rb);
+	}
+}
+
+struct watch_adapter {
+	struct list_head list;
+	struct xenbus_watch watch;
+	struct xenbus_file_priv *dev_data;
+	char *token;
+};
+
+static void free_watch_adapter(struct watch_adapter *watch)
+{
+	kfree(watch->watch.node);
+	kfree(watch->token);
+	kfree(watch);
+}
+
+static struct watch_adapter *alloc_watch_adapter(const char *path,
+						 const char *token)
+{
+	struct watch_adapter *watch;
+
+	watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+	if (watch == NULL)
+		goto out_fail;
+
+	watch->watch.node = kstrdup(path, GFP_KERNEL);
+	if (watch->watch.node == NULL)
+		goto out_free;
+
+	watch->token = kstrdup(token, GFP_KERNEL);
+	if (watch->token == NULL)
+		goto out_free;
+
+	return watch;
+
+out_free:
+	free_watch_adapter(watch);
+
+out_fail:
+	return NULL;
+}
+
+static void watch_fired(struct xenbus_watch *watch,
+			const char **vec,
+			unsigned int len)
+{
+	struct watch_adapter *adap;
+	struct xsd_sockmsg hdr;
+	const char *path, *token;
+	int path_len, tok_len, body_len, data_len = 0;
+	int ret;
+	LIST_HEAD(staging_q);
+
+	adap = container_of(watch, struct watch_adapter, watch);
+
+	path = vec[XS_WATCH_PATH];
+	token = adap->token;
+
+	path_len = strlen(path) + 1;
+	tok_len = strlen(token) + 1;
+	if (len > 2)
+		data_len = vec[len] - vec[2] + 1;
+	body_len = path_len + tok_len + data_len;
+
+	hdr.type = XS_WATCH_EVENT;
+	hdr.len = body_len;
+
+	mutex_lock(&adap->dev_data->reply_mutex);
+
+	ret = queue_reply(&staging_q, &hdr, sizeof(hdr));
+	if (!ret)
+		ret = queue_reply(&staging_q, path, path_len);
+	if (!ret)
+		ret = queue_reply(&staging_q, token, tok_len);
+	if (!ret && len > 2)
+		ret = queue_reply(&staging_q, vec[2], data_len);
+
+	if (!ret) {
+		/* success: pass reply list onto watcher */
+		list_splice_tail(&staging_q, &adap->dev_data->read_buffers);
+		wake_up(&adap->dev_data->read_waitq);
+	} else
+		queue_cleanup(&staging_q);
+
+	mutex_unlock(&adap->dev_data->reply_mutex);
+}
+
+static int xenbus_write_transaction(unsigned msg_type,
+				    struct xenbus_file_priv *u)
+{
+	int rc;
+	void *reply;
+	struct xenbus_transaction_holder *trans = NULL;
+	LIST_HEAD(staging_q);
+
+	if (msg_type == XS_TRANSACTION_START) {
+		trans = kmalloc(sizeof(*trans), GFP_KERNEL);
+		if (!trans) {
+			rc = -ENOMEM;
+			goto out;
+		}
+	}
+
+	reply = xenbus_dev_request_and_reply(&u->u.msg);
+	if (IS_ERR(reply)) {
+		kfree(trans);
+		rc = PTR_ERR(reply);
+		goto out;
+	}
+
+	if (msg_type == XS_TRANSACTION_START) {
+		trans->handle.id = simple_strtoul(reply, NULL, 0);
+
+		list_add(&trans->list, &u->transactions);
+	} else if (msg_type == XS_TRANSACTION_END) {
+		list_for_each_entry(trans, &u->transactions, list)
+			if (trans->handle.id == u->u.msg.tx_id)
+				break;
+		BUG_ON(&trans->list == &u->transactions);
+		list_del(&trans->list);
+
+		kfree(trans);
+	}
+
+	mutex_lock(&u->reply_mutex);
+	rc = queue_reply(&staging_q, &u->u.msg, sizeof(u->u.msg));
+	if (!rc)
+		rc = queue_reply(&staging_q, reply, u->u.msg.len);
+	if (!rc) {
+		list_splice_tail(&staging_q, &u->read_buffers);
+		wake_up(&u->read_waitq);
+	} else {
+		queue_cleanup(&staging_q);
+	}
+	mutex_unlock(&u->reply_mutex);
+
+	kfree(reply);
+
+out:
+	return rc;
+}
+
+static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
+{
+	struct watch_adapter *watch, *tmp_watch;
+	char *path, *token;
+	int err, rc;
+	LIST_HEAD(staging_q);
+
+	path = u->u.buffer + sizeof(u->u.msg);
+	token = memchr(path, 0, u->u.msg.len);
+	if (token == NULL) {
+		rc = -EILSEQ;
+		goto out;
+	}
+	token++;
+	if (memchr(token, 0, u->u.msg.len - (token - path)) == NULL) {
+		rc = -EILSEQ;
+		goto out;
+	}
+
+	if (msg_type == XS_WATCH) {
+		watch = alloc_watch_adapter(path, token);
+		if (watch == NULL) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		watch->watch.callback = watch_fired;
+		watch->dev_data = u;
+
+		err = register_xenbus_watch(&watch->watch);
+		if (err) {
+			free_watch_adapter(watch);
+			rc = err;
+			goto out;
+		}
+		list_add(&watch->list, &u->watches);
+	} else {
+		list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) {
+			if (!strcmp(watch->token, token) &&
+			    !strcmp(watch->watch.node, path)) {
+				unregister_xenbus_watch(&watch->watch);
+				list_del(&watch->list);
+				free_watch_adapter(watch);
+				break;
+			}
+		}
+	}
+
+	/* Success.  Synthesize a reply to say all is OK. */
+	{
+		struct {
+			struct xsd_sockmsg hdr;
+			char body[3];
+		} __packed reply = {
+			{
+				.type = msg_type,
+				.len = sizeof(reply.body)
+			},
+			"OK"
+		};
+
+		mutex_lock(&u->reply_mutex);
+		rc = queue_reply(&u->read_buffers, &reply, sizeof(reply));
+		wake_up(&u->read_waitq);
+		mutex_unlock(&u->reply_mutex);
+	}
+
+out:
+	return rc;
+}
+
+static ssize_t xenbus_file_write(struct file *filp,
+				const char __user *ubuf,
+				size_t len, loff_t *ppos)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+	uint32_t msg_type;
+	int rc = len;
+	int ret;
+	LIST_HEAD(staging_q);
+
+	/*
+	 * We're expecting usermode to be writing properly formed
+	 * xenbus messages.  If they write an incomplete message we
+	 * buffer it up.  Once it is complete, we act on it.
+	 */
+
+	/*
+	 * Make sure concurrent writers can't stomp all over each
+	 * other's messages and make a mess of our partial message
+	 * buffer.  We don't make any attemppt to stop multiple
+	 * writers from making a mess of each other's incomplete
+	 * messages; we're just trying to guarantee our own internal
+	 * consistency and make sure that single writes are handled
+	 * atomically.
+	 */
+	mutex_lock(&u->msgbuffer_mutex);
+
+	/* Get this out of the way early to avoid confusion */
+	if (len == 0)
+		goto out;
+
+	/* Can't write a xenbus message larger we can buffer */
+	if ((len + u->len) > sizeof(u->u.buffer)) {
+		/* On error, dump existing buffer */
+		u->len = 0;
+		rc = -EINVAL;
+		goto out;
+	}
+
+	ret = copy_from_user(u->u.buffer + u->len, ubuf, len);
+
+	if (ret != 0) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	/* Deal with a partial copy. */
+	len -= ret;
+	rc = len;
+
+	u->len += len;
+
+	/* Return if we haven't got a full message yet */
+	if (u->len < sizeof(u->u.msg))
+		goto out;	/* not even the header yet */
+
+	/* If we're expecting a message that's larger than we can
+	   possibly send, dump what we have and return an error. */
+	if ((sizeof(u->u.msg) + u->u.msg.len) > sizeof(u->u.buffer)) {
+		rc = -E2BIG;
+		u->len = 0;
+		goto out;
+	}
+
+	if (u->len < (sizeof(u->u.msg) + u->u.msg.len))
+		goto out;	/* incomplete data portion */
+
+	/*
+	 * OK, now we have a complete message.  Do something with it.
+	 */
+
+	msg_type = u->u.msg.type;
+
+	switch (msg_type) {
+	case XS_WATCH:
+	case XS_UNWATCH:
+		/* (Un)Ask for some path to be watched for changes */
+		ret = xenbus_write_watch(msg_type, u);
+		break;
+
+	default:
+		/* Send out a transaction */
+		ret = xenbus_write_transaction(msg_type, u);
+		break;
+	}
+	if (ret != 0)
+		rc = ret;
+
+	/* Buffered message consumed */
+	u->len = 0;
+
+ out:
+	mutex_unlock(&u->msgbuffer_mutex);
+	return rc;
+}
+
+static int xenbus_file_open(struct inode *inode, struct file *filp)
+{
+	struct xenbus_file_priv *u;
+
+	if (xen_store_evtchn == 0)
+		return -ENOENT;
+
+	nonseekable_open(inode, filp);
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&u->transactions);
+	INIT_LIST_HEAD(&u->watches);
+	INIT_LIST_HEAD(&u->read_buffers);
+	init_waitqueue_head(&u->read_waitq);
+
+	mutex_init(&u->reply_mutex);
+	mutex_init(&u->msgbuffer_mutex);
+
+	filp->private_data = u;
+
+	return 0;
+}
+
+static int xenbus_file_release(struct inode *inode, struct file *filp)
+{
+	struct xenbus_file_priv *u = filp->private_data;
+	struct xenbus_transaction_holder *trans, *tmp;
+	struct watch_adapter *watch, *tmp_watch;
+	struct read_buffer *rb, *tmp_rb;
+
+	/*
+	 * No need for locking here because there are no other users,
+	 * by definition.
+	 */
+
+	list_for_each_entry_safe(trans, tmp, &u->transactions, list) {
+		xenbus_transaction_end(trans->handle, 1);
+		list_del(&trans->list);
+		kfree(trans);
+	}
+
+	list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) {
+		unregister_xenbus_watch(&watch->watch);
+		list_del(&watch->list);
+		free_watch_adapter(watch);
+	}
+
+	list_for_each_entry_safe(rb, tmp_rb, &u->read_buffers, list) {
+		list_del(&rb->list);
+		kfree(rb);
+	}
+	kfree(u);
+
+	return 0;
+}
+
+static unsigned int xenbus_file_poll(struct file *file, poll_table *wait)
+{
+	struct xenbus_file_priv *u = file->private_data;
+
+	poll_wait(file, &u->read_waitq, wait);
+	if (!list_empty(&u->read_buffers))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+const struct file_operations xen_xenbus_fops = {
+	.read = xenbus_file_read,
+	.write = xenbus_file_write,
+	.open = xenbus_file_open,
+	.release = xenbus_file_release,
+	.poll = xenbus_file_poll,
+	.llseek = no_llseek,
+};
+EXPORT_SYMBOL_GPL(xen_xenbus_fops);
+
+static struct miscdevice xenbus_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "xen/xenbus",
+	.fops = &xen_xenbus_fops,
+};
+
+static int __init xenbus_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	err = misc_register(&xenbus_dev);
+	if (err)
+		printk(KERN_ERR "Could not register xenbus frontend device\n");
+	return err;
+}
+
+static void __exit xenbus_exit(void)
+{
+	misc_deregister(&xenbus_dev);
+}
+
+module_init(xenbus_init);
+module_exit(xenbus_exit);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
new file mode 100644
index 00000000..b793723e
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -0,0 +1,777 @@
+/******************************************************************************
+ * Talks to Xen Store to figure out what devices we have.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ * Copyright (C) 2005 Mike Wray, Hewlett-Packard
+ * Copyright (C) 2005, 2006 XenSource Ltd
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#define DPRINTK(fmt, args...)				\
+	pr_debug("xenbus_probe (%s:%d) " fmt ".\n",	\
+		 __func__, __LINE__, ##args)
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/fcntl.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/notifier.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/page.h>
+
+#include <xen/hvm.h>
+
+#include "xenbus_comms.h"
+#include "xenbus_probe.h"
+
+
+int xen_store_evtchn;
+EXPORT_SYMBOL_GPL(xen_store_evtchn);
+
+struct xenstore_domain_interface *xen_store_interface;
+EXPORT_SYMBOL_GPL(xen_store_interface);
+
+static unsigned long xen_store_mfn;
+
+static BLOCKING_NOTIFIER_HEAD(xenstore_chain);
+
+/* If something in array of ids matches this device, return it. */
+static const struct xenbus_device_id *
+match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
+{
+	for (; *arr->devicetype != '\0'; arr++) {
+		if (!strcmp(arr->devicetype, dev->devicetype))
+			return arr;
+	}
+	return NULL;
+}
+
+int xenbus_match(struct device *_dev, struct device_driver *_drv)
+{
+	struct xenbus_driver *drv = to_xenbus_driver(_drv);
+
+	if (!drv->ids)
+		return 0;
+
+	return match_device(drv->ids, to_xenbus_device(_dev)) != NULL;
+}
+EXPORT_SYMBOL_GPL(xenbus_match);
+
+
+static void free_otherend_details(struct xenbus_device *dev)
+{
+	kfree(dev->otherend);
+	dev->otherend = NULL;
+}
+
+
+static void free_otherend_watch(struct xenbus_device *dev)
+{
+	if (dev->otherend_watch.node) {
+		unregister_xenbus_watch(&dev->otherend_watch);
+		kfree(dev->otherend_watch.node);
+		dev->otherend_watch.node = NULL;
+	}
+}
+
+
+static int talk_to_otherend(struct xenbus_device *dev)
+{
+	struct xenbus_driver *drv = to_xenbus_driver(dev->dev.driver);
+
+	free_otherend_watch(dev);
+	free_otherend_details(dev);
+
+	return drv->read_otherend_details(dev);
+}
+
+
+
+static int watch_otherend(struct xenbus_device *dev)
+{
+	struct xen_bus_type *bus =
+		container_of(dev->dev.bus, struct xen_bus_type, bus);
+
+	return xenbus_watch_pathfmt(dev, &dev->otherend_watch,
+				    bus->otherend_changed,
+				    "%s/%s", dev->otherend, "state");
+}
+
+
+int xenbus_read_otherend_details(struct xenbus_device *xendev,
+				 char *id_node, char *path_node)
+{
+	int err = xenbus_gather(XBT_NIL, xendev->nodename,
+				id_node, "%i", &xendev->otherend_id,
+				path_node, NULL, &xendev->otherend,
+				NULL);
+	if (err) {
+		xenbus_dev_fatal(xendev, err,
+				 "reading other end details from %s",
+				 xendev->nodename);
+		return err;
+	}
+	if (strlen(xendev->otherend) == 0 ||
+	    !xenbus_exists(XBT_NIL, xendev->otherend, "")) {
+		xenbus_dev_fatal(xendev, -ENOENT,
+				 "unable to read other end from %s.  "
+				 "missing or inaccessible.",
+				 xendev->nodename);
+		free_otherend_details(xendev);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_read_otherend_details);
+
+void xenbus_otherend_changed(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len,
+			     int ignore_on_shutdown)
+{
+	struct xenbus_device *dev =
+		container_of(watch, struct xenbus_device, otherend_watch);
+	struct xenbus_driver *drv = to_xenbus_driver(dev->dev.driver);
+	enum xenbus_state state;
+
+	/* Protect us against watches firing on old details when the otherend
+	   details change, say immediately after a resume. */
+	if (!dev->otherend ||
+	    strncmp(dev->otherend, vec[XS_WATCH_PATH],
+		    strlen(dev->otherend))) {
+		dev_dbg(&dev->dev, "Ignoring watch at %s\n",
+			vec[XS_WATCH_PATH]);
+		return;
+	}
+
+	state = xenbus_read_driver_state(dev->otherend);
+
+	dev_dbg(&dev->dev, "state is %d, (%s), %s, %s\n",
+		state, xenbus_strstate(state), dev->otherend_watch.node,
+		vec[XS_WATCH_PATH]);
+
+	/*
+	 * Ignore xenbus transitions during shutdown. This prevents us doing
+	 * work that can fail e.g., when the rootfs is gone.
+	 */
+	if (system_state > SYSTEM_RUNNING) {
+		if (ignore_on_shutdown && (state == XenbusStateClosing))
+			xenbus_frontend_closed(dev);
+		return;
+	}
+
+	if (drv->otherend_changed)
+		drv->otherend_changed(dev, state);
+}
+EXPORT_SYMBOL_GPL(xenbus_otherend_changed);
+
+int xenbus_dev_probe(struct device *_dev)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+	struct xenbus_driver *drv = to_xenbus_driver(_dev->driver);
+	const struct xenbus_device_id *id;
+	int err;
+
+	DPRINTK("%s", dev->nodename);
+
+	if (!drv->probe) {
+		err = -ENODEV;
+		goto fail;
+	}
+
+	id = match_device(drv->ids, dev);
+	if (!id) {
+		err = -ENODEV;
+		goto fail;
+	}
+
+	err = talk_to_otherend(dev);
+	if (err) {
+		dev_warn(&dev->dev, "talk_to_otherend on %s failed.\n",
+			 dev->nodename);
+		return err;
+	}
+
+	err = drv->probe(dev, id);
+	if (err)
+		goto fail;
+
+	err = watch_otherend(dev);
+	if (err) {
+		dev_warn(&dev->dev, "watch_otherend on %s failed.\n",
+		       dev->nodename);
+		return err;
+	}
+
+	return 0;
+fail:
+	xenbus_dev_error(dev, err, "xenbus_dev_probe on %s", dev->nodename);
+	xenbus_switch_state(dev, XenbusStateClosed);
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_probe);
+
+int xenbus_dev_remove(struct device *_dev)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+	struct xenbus_driver *drv = to_xenbus_driver(_dev->driver);
+
+	DPRINTK("%s", dev->nodename);
+
+	free_otherend_watch(dev);
+
+	if (drv->remove)
+		drv->remove(dev);
+
+	free_otherend_details(dev);
+
+	xenbus_switch_state(dev, XenbusStateClosed);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_remove);
+
+void xenbus_dev_shutdown(struct device *_dev)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+	unsigned long timeout = 5*HZ;
+
+	DPRINTK("%s", dev->nodename);
+
+	get_device(&dev->dev);
+	if (dev->state != XenbusStateConnected) {
+		printk(KERN_INFO "%s: %s: %s != Connected, skipping\n", __func__,
+		       dev->nodename, xenbus_strstate(dev->state));
+		goto out;
+	}
+	xenbus_switch_state(dev, XenbusStateClosing);
+	timeout = wait_for_completion_timeout(&dev->down, timeout);
+	if (!timeout)
+		printk(KERN_INFO "%s: %s timeout closing device\n",
+		       __func__, dev->nodename);
+ out:
+	put_device(&dev->dev);
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_shutdown);
+
+int xenbus_register_driver_common(struct xenbus_driver *drv,
+				  struct xen_bus_type *bus)
+{
+	drv->driver.bus = &bus->bus;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(xenbus_register_driver_common);
+
+void xenbus_unregister_driver(struct xenbus_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(xenbus_unregister_driver);
+
+struct xb_find_info {
+	struct xenbus_device *dev;
+	const char *nodename;
+};
+
+static int cmp_dev(struct device *dev, void *data)
+{
+	struct xenbus_device *xendev = to_xenbus_device(dev);
+	struct xb_find_info *info = data;
+
+	if (!strcmp(xendev->nodename, info->nodename)) {
+		info->dev = xendev;
+		get_device(dev);
+		return 1;
+	}
+	return 0;
+}
+
+struct xenbus_device *xenbus_device_find(const char *nodename,
+					 struct bus_type *bus)
+{
+	struct xb_find_info info = { .dev = NULL, .nodename = nodename };
+
+	bus_for_each_dev(bus, NULL, &info, cmp_dev);
+	return info.dev;
+}
+
+static int cleanup_dev(struct device *dev, void *data)
+{
+	struct xenbus_device *xendev = to_xenbus_device(dev);
+	struct xb_find_info *info = data;
+	int len = strlen(info->nodename);
+
+	DPRINTK("%s", info->nodename);
+
+	/* Match the info->nodename path, or any subdirectory of that path. */
+	if (strncmp(xendev->nodename, info->nodename, len))
+		return 0;
+
+	/* If the node name is longer, ensure it really is a subdirectory. */
+	if ((strlen(xendev->nodename) > len) && (xendev->nodename[len] != '/'))
+		return 0;
+
+	info->dev = xendev;
+	get_device(dev);
+	return 1;
+}
+
+static void xenbus_cleanup_devices(const char *path, struct bus_type *bus)
+{
+	struct xb_find_info info = { .nodename = path };
+
+	do {
+		info.dev = NULL;
+		bus_for_each_dev(bus, NULL, &info, cleanup_dev);
+		if (info.dev) {
+			device_unregister(&info.dev->dev);
+			put_device(&info.dev->dev);
+		}
+	} while (info.dev);
+}
+
+static void xenbus_dev_release(struct device *dev)
+{
+	if (dev)
+		kfree(to_xenbus_device(dev));
+}
+
+static ssize_t nodename_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s\n", to_xenbus_device(dev)->nodename);
+}
+
+static ssize_t devtype_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s\n", to_xenbus_device(dev)->devicetype);
+}
+
+static ssize_t modalias_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s:%s\n", dev->bus->name,
+		       to_xenbus_device(dev)->devicetype);
+}
+
+struct device_attribute xenbus_dev_attrs[] = {
+	__ATTR_RO(nodename),
+	__ATTR_RO(devtype),
+	__ATTR_RO(modalias),
+	__ATTR_NULL
+};
+EXPORT_SYMBOL_GPL(xenbus_dev_attrs);
+
+int xenbus_probe_node(struct xen_bus_type *bus,
+		      const char *type,
+		      const char *nodename)
+{
+	char devname[XEN_BUS_ID_SIZE];
+	int err;
+	struct xenbus_device *xendev;
+	size_t stringlen;
+	char *tmpstring;
+
+	enum xenbus_state state = xenbus_read_driver_state(nodename);
+
+	if (state != XenbusStateInitialising) {
+		/* Device is not new, so ignore it.  This can happen if a
+		   device is going away after switching to Closed.  */
+		return 0;
+	}
+
+	stringlen = strlen(nodename) + 1 + strlen(type) + 1;
+	xendev = kzalloc(sizeof(*xendev) + stringlen, GFP_KERNEL);
+	if (!xendev)
+		return -ENOMEM;
+
+	xendev->state = XenbusStateInitialising;
+
+	/* Copy the strings into the extra space. */
+
+	tmpstring = (char *)(xendev + 1);
+	strcpy(tmpstring, nodename);
+	xendev->nodename = tmpstring;
+
+	tmpstring += strlen(tmpstring) + 1;
+	strcpy(tmpstring, type);
+	xendev->devicetype = tmpstring;
+	init_completion(&xendev->down);
+
+	xendev->dev.bus = &bus->bus;
+	xendev->dev.release = xenbus_dev_release;
+
+	err = bus->get_bus_id(devname, xendev->nodename);
+	if (err)
+		goto fail;
+
+	dev_set_name(&xendev->dev, devname);
+
+	/* Register with generic device framework. */
+	err = device_register(&xendev->dev);
+	if (err)
+		goto fail;
+
+	return 0;
+fail:
+	kfree(xendev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_probe_node);
+
+static int xenbus_probe_device_type(struct xen_bus_type *bus, const char *type)
+{
+	int err = 0;
+	char **dir;
+	unsigned int dir_n = 0;
+	int i;
+
+	dir = xenbus_directory(XBT_NIL, bus->root, type, &dir_n);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	for (i = 0; i < dir_n; i++) {
+		err = bus->probe(bus, type, dir[i]);
+		if (err)
+			break;
+	}
+
+	kfree(dir);
+	return err;
+}
+
+int xenbus_probe_devices(struct xen_bus_type *bus)
+{
+	int err = 0;
+	char **dir;
+	unsigned int i, dir_n;
+
+	dir = xenbus_directory(XBT_NIL, bus->root, "", &dir_n);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	for (i = 0; i < dir_n; i++) {
+		err = xenbus_probe_device_type(bus, dir[i]);
+		if (err)
+			break;
+	}
+
+	kfree(dir);
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_probe_devices);
+
+static unsigned int char_count(const char *str, char c)
+{
+	unsigned int i, ret = 0;
+
+	for (i = 0; str[i]; i++)
+		if (str[i] == c)
+			ret++;
+	return ret;
+}
+
+static int strsep_len(const char *str, char c, unsigned int len)
+{
+	unsigned int i;
+
+	for (i = 0; str[i]; i++)
+		if (str[i] == c) {
+			if (len == 0)
+				return i;
+			len--;
+		}
+	return (len == 0) ? i : -ERANGE;
+}
+
+void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
+{
+	int exists, rootlen;
+	struct xenbus_device *dev;
+	char type[XEN_BUS_ID_SIZE];
+	const char *p, *root;
+
+	if (char_count(node, '/') < 2)
+		return;
+
+	exists = xenbus_exists(XBT_NIL, node, "");
+	if (!exists) {
+		xenbus_cleanup_devices(node, &bus->bus);
+		return;
+	}
+
+	/* backend/<type>/... or device/<type>/... */
+	p = strchr(node, '/') + 1;
+	snprintf(type, XEN_BUS_ID_SIZE, "%.*s", (int)strcspn(p, "/"), p);
+	type[XEN_BUS_ID_SIZE-1] = '\0';
+
+	rootlen = strsep_len(node, '/', bus->levels);
+	if (rootlen < 0)
+		return;
+	root = kasprintf(GFP_KERNEL, "%.*s", rootlen, node);
+	if (!root)
+		return;
+
+	dev = xenbus_device_find(root, &bus->bus);
+	if (!dev)
+		xenbus_probe_node(bus, type, root);
+	else
+		put_device(&dev->dev);
+
+	kfree(root);
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_changed);
+
+int xenbus_dev_suspend(struct device *dev)
+{
+	int err = 0;
+	struct xenbus_driver *drv;
+	struct xenbus_device *xdev
+		= container_of(dev, struct xenbus_device, dev);
+
+	DPRINTK("%s", xdev->nodename);
+
+	if (dev->driver == NULL)
+		return 0;
+	drv = to_xenbus_driver(dev->driver);
+	if (drv->suspend)
+		err = drv->suspend(xdev);
+	if (err)
+		printk(KERN_WARNING
+		       "xenbus: suspend %s failed: %i\n", dev_name(dev), err);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_suspend);
+
+int xenbus_dev_resume(struct device *dev)
+{
+	int err;
+	struct xenbus_driver *drv;
+	struct xenbus_device *xdev
+		= container_of(dev, struct xenbus_device, dev);
+
+	DPRINTK("%s", xdev->nodename);
+
+	if (dev->driver == NULL)
+		return 0;
+	drv = to_xenbus_driver(dev->driver);
+	err = talk_to_otherend(xdev);
+	if (err) {
+		printk(KERN_WARNING
+		       "xenbus: resume (talk_to_otherend) %s failed: %i\n",
+		       dev_name(dev), err);
+		return err;
+	}
+
+	xdev->state = XenbusStateInitialising;
+
+	if (drv->resume) {
+		err = drv->resume(xdev);
+		if (err) {
+			printk(KERN_WARNING
+			       "xenbus: resume %s failed: %i\n",
+			       dev_name(dev), err);
+			return err;
+		}
+	}
+
+	err = watch_otherend(xdev);
+	if (err) {
+		printk(KERN_WARNING
+		       "xenbus_probe: resume (watch_otherend) %s failed: "
+		       "%d.\n", dev_name(dev), err);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_resume);
+
+int xenbus_dev_cancel(struct device *dev)
+{
+	/* Do nothing */
+	DPRINTK("cancel");
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_cancel);
+
+/* A flag to determine if xenstored is 'ready' (i.e. has started) */
+int xenstored_ready;
+
+
+int register_xenstore_notifier(struct notifier_block *nb)
+{
+	int ret = 0;
+
+	if (xenstored_ready > 0)
+		ret = nb->notifier_call(nb, 0, NULL);
+	else
+		blocking_notifier_chain_register(&xenstore_chain, nb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_xenstore_notifier);
+
+void unregister_xenstore_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&xenstore_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
+
+void xenbus_probe(struct work_struct *unused)
+{
+	xenstored_ready = 1;
+
+	/* Notify others that xenstore is up */
+	blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(xenbus_probe);
+
+static int __init xenbus_probe_initcall(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (xen_initial_domain() || xen_hvm_domain())
+		return 0;
+
+	xenbus_probe(NULL);
+	return 0;
+}
+
+device_initcall(xenbus_probe_initcall);
+
+/* Set up event channel for xenstored which is run as a local process
+ * (this is normally used only in dom0)
+ */
+static int __init xenstored_local_init(void)
+{
+	int err = 0;
+	unsigned long page = 0;
+	struct evtchn_alloc_unbound alloc_unbound;
+
+	/* Allocate Xenstore page */
+	page = get_zeroed_page(GFP_KERNEL);
+	if (!page)
+		goto out_err;
+
+	xen_store_mfn = xen_start_info->store_mfn =
+		pfn_to_mfn(virt_to_phys((void *)page) >>
+			   PAGE_SHIFT);
+
+	/* Next allocate a local port which xenstored can bind to */
+	alloc_unbound.dom        = DOMID_SELF;
+	alloc_unbound.remote_dom = DOMID_SELF;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+					  &alloc_unbound);
+	if (err == -ENOSYS)
+		goto out_err;
+
+	BUG_ON(err);
+	xen_store_evtchn = xen_start_info->store_evtchn =
+		alloc_unbound.port;
+
+	return 0;
+
+ out_err:
+	if (page != 0)
+		free_page(page);
+	return err;
+}
+
+static int __init xenbus_init(void)
+{
+	int err = 0;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	xenbus_ring_ops_init();
+
+	if (xen_hvm_domain()) {
+		uint64_t v = 0;
+		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+		if (err)
+			goto out_error;
+		xen_store_evtchn = (int)v;
+		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
+		if (err)
+			goto out_error;
+		xen_store_mfn = (unsigned long)v;
+		xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
+	} else {
+		xen_store_evtchn = xen_start_info->store_evtchn;
+		xen_store_mfn = xen_start_info->store_mfn;
+		if (xen_store_evtchn)
+			xenstored_ready = 1;
+		else {
+			err = xenstored_local_init();
+			if (err)
+				goto out_error;
+		}
+		xen_store_interface = mfn_to_virt(xen_store_mfn);
+	}
+
+	/* Initialize the interface to xenstore. */
+	err = xs_init();
+	if (err) {
+		printk(KERN_WARNING
+		       "XENBUS: Error initializing xenstore comms: %i\n", err);
+		goto out_error;
+	}
+
+#ifdef CONFIG_XEN_COMPAT_XENFS
+	/*
+	 * Create xenfs mountpoint in /proc for compatibility with
+	 * utilities that expect to find "xenbus" under "/proc/xen".
+	 */
+	proc_mkdir("xen", NULL);
+#endif
+
+out_error:
+	return err;
+}
+
+postcore_initcall(xenbus_init);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/xenbus/xenbus_probe.h b/drivers/xen/xenbus/xenbus_probe.h
new file mode 100644
index 00000000..bb4f92ed
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_probe.h
@@ -0,0 +1,79 @@
+/******************************************************************************
+ * xenbus_probe.h
+ *
+ * Talks to Xen Store to figure out what devices we have.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ * Copyright (C) 2005 XenSource Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _XENBUS_PROBE_H
+#define _XENBUS_PROBE_H
+
+#define XEN_BUS_ID_SIZE			20
+
+struct xen_bus_type {
+	char *root;
+	unsigned int levels;
+	int (*get_bus_id)(char bus_id[XEN_BUS_ID_SIZE], const char *nodename);
+	int (*probe)(struct xen_bus_type *bus, const char *type,
+		     const char *dir);
+	void (*otherend_changed)(struct xenbus_watch *watch, const char **vec,
+				 unsigned int len);
+	struct bus_type bus;
+};
+
+extern struct device_attribute xenbus_dev_attrs[];
+
+extern int xenbus_match(struct device *_dev, struct device_driver *_drv);
+extern int xenbus_dev_probe(struct device *_dev);
+extern int xenbus_dev_remove(struct device *_dev);
+extern int xenbus_register_driver_common(struct xenbus_driver *drv,
+					 struct xen_bus_type *bus);
+extern int xenbus_probe_node(struct xen_bus_type *bus,
+			     const char *type,
+			     const char *nodename);
+extern int xenbus_probe_devices(struct xen_bus_type *bus);
+
+extern void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
+
+extern void xenbus_dev_shutdown(struct device *_dev);
+
+extern int xenbus_dev_suspend(struct device *dev);
+extern int xenbus_dev_resume(struct device *dev);
+extern int xenbus_dev_cancel(struct device *dev);
+
+extern void xenbus_otherend_changed(struct xenbus_watch *watch,
+				    const char **vec, unsigned int len,
+				    int ignore_on_shutdown);
+
+extern int xenbus_read_otherend_details(struct xenbus_device *xendev,
+					char *id_node, char *path_node);
+
+void xenbus_ring_ops_init(void);
+
+#endif
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
new file mode 100644
index 00000000..257be37d
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -0,0 +1,272 @@
+/******************************************************************************
+ * Talks to Xen Store to figure out what devices we have (backend half).
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ * Copyright (C) 2005 Mike Wray, Hewlett-Packard
+ * Copyright (C) 2005, 2006 XenSource Ltd
+ * Copyright (C) 2007 Solarflare Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#define DPRINTK(fmt, args...)				\
+	pr_debug("xenbus_probe (%s:%d) " fmt ".\n",	\
+		 __func__, __LINE__, ##args)
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/fcntl.h>
+#include <linux/mm.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/hypervisor.h>
+#include <xen/xenbus.h>
+#include <xen/features.h>
+
+#include "xenbus_comms.h"
+#include "xenbus_probe.h"
+
+/* backend/<type>/<fe-uuid>/<id> => <type>-<fe-domid>-<id> */
+static int backend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename)
+{
+	int domid, err;
+	const char *devid, *type, *frontend;
+	unsigned int typelen;
+
+	type = strchr(nodename, '/');
+	if (!type)
+		return -EINVAL;
+	type++;
+	typelen = strcspn(type, "/");
+	if (!typelen || type[typelen] != '/')
+		return -EINVAL;
+
+	devid = strrchr(nodename, '/') + 1;
+
+	err = xenbus_gather(XBT_NIL, nodename, "frontend-id", "%i", &domid,
+			    "frontend", NULL, &frontend,
+			    NULL);
+	if (err)
+		return err;
+	if (strlen(frontend) == 0)
+		err = -ERANGE;
+	if (!err && !xenbus_exists(XBT_NIL, frontend, ""))
+		err = -ENOENT;
+	kfree(frontend);
+
+	if (err)
+		return err;
+
+	if (snprintf(bus_id, XEN_BUS_ID_SIZE, "%.*s-%i-%s",
+		     typelen, type, domid, devid) >= XEN_BUS_ID_SIZE)
+		return -ENOSPC;
+	return 0;
+}
+
+static int xenbus_uevent_backend(struct device *dev,
+				 struct kobj_uevent_env *env)
+{
+	struct xenbus_device *xdev;
+	struct xenbus_driver *drv;
+	struct xen_bus_type *bus;
+
+	DPRINTK("");
+
+	if (dev == NULL)
+		return -ENODEV;
+
+	xdev = to_xenbus_device(dev);
+	bus = container_of(xdev->dev.bus, struct xen_bus_type, bus);
+
+	if (add_uevent_var(env, "MODALIAS=xen-backend:%s", xdev->devicetype))
+		return -ENOMEM;
+
+	/* stuff we want to pass to /sbin/hotplug */
+	if (add_uevent_var(env, "XENBUS_TYPE=%s", xdev->devicetype))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "XENBUS_PATH=%s", xdev->nodename))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "XENBUS_BASE_PATH=%s", bus->root))
+		return -ENOMEM;
+
+	if (dev->driver) {
+		drv = to_xenbus_driver(dev->driver);
+		if (drv && drv->uevent)
+			return drv->uevent(xdev, env);
+	}
+
+	return 0;
+}
+
+/* backend/<typename>/<frontend-uuid>/<name> */
+static int xenbus_probe_backend_unit(struct xen_bus_type *bus,
+				     const char *dir,
+				     const char *type,
+				     const char *name)
+{
+	char *nodename;
+	int err;
+
+	nodename = kasprintf(GFP_KERNEL, "%s/%s", dir, name);
+	if (!nodename)
+		return -ENOMEM;
+
+	DPRINTK("%s\n", nodename);
+
+	err = xenbus_probe_node(bus, type, nodename);
+	kfree(nodename);
+	return err;
+}
+
+/* backend/<typename>/<frontend-domid> */
+static int xenbus_probe_backend(struct xen_bus_type *bus, const char *type,
+				const char *domid)
+{
+	char *nodename;
+	int err = 0;
+	char **dir;
+	unsigned int i, dir_n = 0;
+
+	DPRINTK("");
+
+	nodename = kasprintf(GFP_KERNEL, "%s/%s/%s", bus->root, type, domid);
+	if (!nodename)
+		return -ENOMEM;
+
+	dir = xenbus_directory(XBT_NIL, nodename, "", &dir_n);
+	if (IS_ERR(dir)) {
+		kfree(nodename);
+		return PTR_ERR(dir);
+	}
+
+	for (i = 0; i < dir_n; i++) {
+		err = xenbus_probe_backend_unit(bus, nodename, type, dir[i]);
+		if (err)
+			break;
+	}
+	kfree(dir);
+	kfree(nodename);
+	return err;
+}
+
+static void frontend_changed(struct xenbus_watch *watch,
+			    const char **vec, unsigned int len)
+{
+	xenbus_otherend_changed(watch, vec, len, 0);
+}
+
+static struct xen_bus_type xenbus_backend = {
+	.root = "backend",
+	.levels = 3,		/* backend/type/<frontend>/<id> */
+	.get_bus_id = backend_bus_id,
+	.probe = xenbus_probe_backend,
+	.otherend_changed = frontend_changed,
+	.bus = {
+		.name		= "xen-backend",
+		.match		= xenbus_match,
+		.uevent		= xenbus_uevent_backend,
+		.probe		= xenbus_dev_probe,
+		.remove		= xenbus_dev_remove,
+		.shutdown	= xenbus_dev_shutdown,
+		.dev_attrs	= xenbus_dev_attrs,
+	},
+};
+
+static void backend_changed(struct xenbus_watch *watch,
+			    const char **vec, unsigned int len)
+{
+	DPRINTK("");
+
+	xenbus_dev_changed(vec[XS_WATCH_PATH], &xenbus_backend);
+}
+
+static struct xenbus_watch be_watch = {
+	.node = "backend",
+	.callback = backend_changed,
+};
+
+static int read_frontend_details(struct xenbus_device *xendev)
+{
+	return xenbus_read_otherend_details(xendev, "frontend-id", "frontend");
+}
+
+int xenbus_dev_is_online(struct xenbus_device *dev)
+{
+	int rc, val;
+
+	rc = xenbus_scanf(XBT_NIL, dev->nodename, "online", "%d", &val);
+	if (rc != 1)
+		val = 0; /* no online node present */
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(xenbus_dev_is_online);
+
+int xenbus_register_backend(struct xenbus_driver *drv)
+{
+	drv->read_otherend_details = read_frontend_details;
+
+	return xenbus_register_driver_common(drv, &xenbus_backend);
+}
+EXPORT_SYMBOL_GPL(xenbus_register_backend);
+
+static int backend_probe_and_watch(struct notifier_block *notifier,
+				   unsigned long event,
+				   void *data)
+{
+	/* Enumerate devices in xenstore and watch for changes. */
+	xenbus_probe_devices(&xenbus_backend);
+	register_xenbus_watch(&be_watch);
+
+	return NOTIFY_DONE;
+}
+
+static int __init xenbus_probe_backend_init(void)
+{
+	static struct notifier_block xenstore_notifier = {
+		.notifier_call = backend_probe_and_watch
+	};
+	int err;
+
+	DPRINTK("");
+
+	/* Register ourselves with the kernel bus subsystem */
+	err = bus_register(&xenbus_backend.bus);
+	if (err)
+		return err;
+
+	register_xenstore_notifier(&xenstore_notifier);
+
+	return 0;
+}
+subsys_initcall(xenbus_probe_backend_init);
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
new file mode 100644
index 00000000..a31b54d4
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -0,0 +1,460 @@
+#define DPRINTK(fmt, args...)				\
+	pr_debug("xenbus_probe (%s:%d) " fmt ".\n",	\
+		 __func__, __LINE__, ##args)
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/fcntl.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/notifier.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/module.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/xen/hypervisor.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/page.h>
+
+#include <xen/platform_pci.h>
+
+#include "xenbus_comms.h"
+#include "xenbus_probe.h"
+
+
+/* device/<type>/<id> => <type>-<id> */
+static int frontend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename)
+{
+	nodename = strchr(nodename, '/');
+	if (!nodename || strlen(nodename + 1) >= XEN_BUS_ID_SIZE) {
+		printk(KERN_WARNING "XENBUS: bad frontend %s\n", nodename);
+		return -EINVAL;
+	}
+
+	strlcpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE);
+	if (!strchr(bus_id, '/')) {
+		printk(KERN_WARNING "XENBUS: bus_id %s no slash\n", bus_id);
+		return -EINVAL;
+	}
+	*strchr(bus_id, '/') = '-';
+	return 0;
+}
+
+/* device/<typename>/<name> */
+static int xenbus_probe_frontend(struct xen_bus_type *bus, const char *type,
+				 const char *name)
+{
+	char *nodename;
+	int err;
+
+	/* ignore console/0 */
+	if (!strncmp(type, "console", 7) && !strncmp(name, "0", 1)) {
+		DPRINTK("Ignoring buggy device entry console/0");
+		return 0;
+	}
+
+	nodename = kasprintf(GFP_KERNEL, "%s/%s/%s", bus->root, type, name);
+	if (!nodename)
+		return -ENOMEM;
+
+	DPRINTK("%s", nodename);
+
+	err = xenbus_probe_node(bus, type, nodename);
+	kfree(nodename);
+	return err;
+}
+
+static int xenbus_uevent_frontend(struct device *_dev,
+				  struct kobj_uevent_env *env)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+
+	if (add_uevent_var(env, "MODALIAS=xen:%s", dev->devicetype))
+		return -ENOMEM;
+
+	return 0;
+}
+
+
+static void backend_changed(struct xenbus_watch *watch,
+			    const char **vec, unsigned int len)
+{
+	xenbus_otherend_changed(watch, vec, len, 1);
+}
+
+static const struct dev_pm_ops xenbus_pm_ops = {
+	.suspend	= xenbus_dev_suspend,
+	.resume		= xenbus_dev_resume,
+	.freeze		= xenbus_dev_suspend,
+	.thaw		= xenbus_dev_cancel,
+	.restore	= xenbus_dev_resume,
+};
+
+static struct xen_bus_type xenbus_frontend = {
+	.root = "device",
+	.levels = 2,		/* device/type/<id> */
+	.get_bus_id = frontend_bus_id,
+	.probe = xenbus_probe_frontend,
+	.otherend_changed = backend_changed,
+	.bus = {
+		.name		= "xen",
+		.match		= xenbus_match,
+		.uevent		= xenbus_uevent_frontend,
+		.probe		= xenbus_dev_probe,
+		.remove		= xenbus_dev_remove,
+		.shutdown	= xenbus_dev_shutdown,
+		.dev_attrs	= xenbus_dev_attrs,
+
+		.pm		= &xenbus_pm_ops,
+	},
+};
+
+static void frontend_changed(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len)
+{
+	DPRINTK("");
+
+	xenbus_dev_changed(vec[XS_WATCH_PATH], &xenbus_frontend);
+}
+
+
+/* We watch for devices appearing and vanishing. */
+static struct xenbus_watch fe_watch = {
+	.node = "device",
+	.callback = frontend_changed,
+};
+
+static int read_backend_details(struct xenbus_device *xendev)
+{
+	return xenbus_read_otherend_details(xendev, "backend-id", "backend");
+}
+
+static int is_device_connecting(struct device *dev, void *data, bool ignore_nonessential)
+{
+	struct xenbus_device *xendev = to_xenbus_device(dev);
+	struct device_driver *drv = data;
+	struct xenbus_driver *xendrv;
+
+	/*
+	 * A device with no driver will never connect. We care only about
+	 * devices which should currently be in the process of connecting.
+	 */
+	if (!dev->driver)
+		return 0;
+
+	/* Is this search limited to a particular driver? */
+	if (drv && (dev->driver != drv))
+		return 0;
+
+	if (ignore_nonessential) {
+		/* With older QEMU, for PVonHVM guests the guest config files
+		 * could contain: vfb = [ 'vnc=1, vnclisten=0.0.0.0']
+		 * which is nonsensical as there is no PV FB (there can be
+		 * a PVKB) running as HVM guest. */
+
+		if ((strncmp(xendev->nodename, "device/vkbd", 11) == 0))
+			return 0;
+
+		if ((strncmp(xendev->nodename, "device/vfb", 10) == 0))
+			return 0;
+	}
+	xendrv = to_xenbus_driver(dev->driver);
+	return (xendev->state < XenbusStateConnected ||
+		(xendev->state == XenbusStateConnected &&
+		 xendrv->is_ready && !xendrv->is_ready(xendev)));
+}
+static int essential_device_connecting(struct device *dev, void *data)
+{
+	return is_device_connecting(dev, data, true /* ignore PV[KBB+FB] */);
+}
+static int non_essential_device_connecting(struct device *dev, void *data)
+{
+	return is_device_connecting(dev, data, false);
+}
+
+static int exists_essential_connecting_device(struct device_driver *drv)
+{
+	return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
+				essential_device_connecting);
+}
+static int exists_non_essential_connecting_device(struct device_driver *drv)
+{
+	return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
+				non_essential_device_connecting);
+}
+
+static int print_device_status(struct device *dev, void *data)
+{
+	struct xenbus_device *xendev = to_xenbus_device(dev);
+	struct device_driver *drv = data;
+
+	/* Is this operation limited to a particular driver? */
+	if (drv && (dev->driver != drv))
+		return 0;
+
+	if (!dev->driver) {
+		/* Information only: is this too noisy? */
+		printk(KERN_INFO "XENBUS: Device with no driver: %s\n",
+		       xendev->nodename);
+	} else if (xendev->state < XenbusStateConnected) {
+		enum xenbus_state rstate = XenbusStateUnknown;
+		if (xendev->otherend)
+			rstate = xenbus_read_driver_state(xendev->otherend);
+		printk(KERN_WARNING "XENBUS: Timeout connecting "
+		       "to device: %s (local state %d, remote state %d)\n",
+		       xendev->nodename, xendev->state, rstate);
+	}
+
+	return 0;
+}
+
+/* We only wait for device setup after most initcalls have run. */
+static int ready_to_wait_for_devices;
+
+static bool wait_loop(unsigned long start, unsigned int max_delay,
+		     unsigned int *seconds_waited)
+{
+	if (time_after(jiffies, start + (*seconds_waited+5)*HZ)) {
+		if (!*seconds_waited)
+			printk(KERN_WARNING "XENBUS: Waiting for "
+			       "devices to initialise: ");
+		*seconds_waited += 5;
+		printk("%us...", max_delay - *seconds_waited);
+		if (*seconds_waited == max_delay)
+			return true;
+	}
+
+	schedule_timeout_interruptible(HZ/10);
+
+	return false;
+}
+/*
+ * On a 5-minute timeout, wait for all devices currently configured.  We need
+ * to do this to guarantee that the filesystems and / or network devices
+ * needed for boot are available, before we can allow the boot to proceed.
+ *
+ * This needs to be on a late_initcall, to happen after the frontend device
+ * drivers have been initialised, but before the root fs is mounted.
+ *
+ * A possible improvement here would be to have the tools add a per-device
+ * flag to the store entry, indicating whether it is needed at boot time.
+ * This would allow people who knew what they were doing to accelerate their
+ * boot slightly, but of course needs tools or manual intervention to set up
+ * those flags correctly.
+ */
+static void wait_for_devices(struct xenbus_driver *xendrv)
+{
+	unsigned long start = jiffies;
+	struct device_driver *drv = xendrv ? &xendrv->driver : NULL;
+	unsigned int seconds_waited = 0;
+
+	if (!ready_to_wait_for_devices || !xen_domain())
+		return;
+
+	while (exists_non_essential_connecting_device(drv))
+		if (wait_loop(start, 30, &seconds_waited))
+			break;
+
+	/* Skips PVKB and PVFB check.*/
+	while (exists_essential_connecting_device(drv))
+		if (wait_loop(start, 270, &seconds_waited))
+			break;
+
+	if (seconds_waited)
+		printk("\n");
+
+	bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
+			 print_device_status);
+}
+
+int xenbus_register_frontend(struct xenbus_driver *drv)
+{
+	int ret;
+
+	drv->read_otherend_details = read_backend_details;
+
+	ret = xenbus_register_driver_common(drv, &xenbus_frontend);
+	if (ret)
+		return ret;
+
+	/* If this driver is loaded as a module wait for devices to attach. */
+	wait_for_devices(drv);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_register_frontend);
+
+static DECLARE_WAIT_QUEUE_HEAD(backend_state_wq);
+static int backend_state;
+
+static void xenbus_reset_backend_state_changed(struct xenbus_watch *w,
+					const char **v, unsigned int l)
+{
+	xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state);
+	printk(KERN_DEBUG "XENBUS: backend %s %s\n",
+			v[XS_WATCH_PATH], xenbus_strstate(backend_state));
+	wake_up(&backend_state_wq);
+}
+
+static void xenbus_reset_wait_for_backend(char *be, int expected)
+{
+	long timeout;
+	timeout = wait_event_interruptible_timeout(backend_state_wq,
+			backend_state == expected, 5 * HZ);
+	if (timeout <= 0)
+		printk(KERN_INFO "XENBUS: backend %s timed out.\n", be);
+}
+
+/*
+ * Reset frontend if it is in Connected or Closed state.
+ * Wait for backend to catch up.
+ * State Connected happens during kdump, Closed after kexec.
+ */
+static void xenbus_reset_frontend(char *fe, char *be, int be_state)
+{
+	struct xenbus_watch be_watch;
+
+	printk(KERN_DEBUG "XENBUS: backend %s %s\n",
+			be, xenbus_strstate(be_state));
+
+	memset(&be_watch, 0, sizeof(be_watch));
+	be_watch.node = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/state", be);
+	if (!be_watch.node)
+		return;
+
+	be_watch.callback = xenbus_reset_backend_state_changed;
+	backend_state = XenbusStateUnknown;
+
+	printk(KERN_INFO "XENBUS: triggering reconnect on %s\n", be);
+	register_xenbus_watch(&be_watch);
+
+	/* fall through to forward backend to state XenbusStateInitialising */
+	switch (be_state) {
+	case XenbusStateConnected:
+		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing);
+		xenbus_reset_wait_for_backend(be, XenbusStateClosing);
+
+	case XenbusStateClosing:
+		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed);
+		xenbus_reset_wait_for_backend(be, XenbusStateClosed);
+
+	case XenbusStateClosed:
+		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising);
+		xenbus_reset_wait_for_backend(be, XenbusStateInitWait);
+	}
+
+	unregister_xenbus_watch(&be_watch);
+	printk(KERN_INFO "XENBUS: reconnect done on %s\n", be);
+	kfree(be_watch.node);
+}
+
+static void xenbus_check_frontend(char *class, char *dev)
+{
+	int be_state, fe_state, err;
+	char *backend, *frontend;
+
+	frontend = kasprintf(GFP_NOIO | __GFP_HIGH, "device/%s/%s", class, dev);
+	if (!frontend)
+		return;
+
+	err = xenbus_scanf(XBT_NIL, frontend, "state", "%i", &fe_state);
+	if (err != 1)
+		goto out;
+
+	switch (fe_state) {
+	case XenbusStateConnected:
+	case XenbusStateClosed:
+		printk(KERN_DEBUG "XENBUS: frontend %s %s\n",
+				frontend, xenbus_strstate(fe_state));
+		backend = xenbus_read(XBT_NIL, frontend, "backend", NULL);
+		if (!backend || IS_ERR(backend))
+			goto out;
+		err = xenbus_scanf(XBT_NIL, backend, "state", "%i", &be_state);
+		if (err == 1)
+			xenbus_reset_frontend(frontend, backend, be_state);
+		kfree(backend);
+		break;
+	default:
+		break;
+	}
+out:
+	kfree(frontend);
+}
+
+static void xenbus_reset_state(void)
+{
+	char **devclass, **dev;
+	int devclass_n, dev_n;
+	int i, j;
+
+	devclass = xenbus_directory(XBT_NIL, "device", "", &devclass_n);
+	if (IS_ERR(devclass))
+		return;
+
+	for (i = 0; i < devclass_n; i++) {
+		dev = xenbus_directory(XBT_NIL, "device", devclass[i], &dev_n);
+		if (IS_ERR(dev))
+			continue;
+		for (j = 0; j < dev_n; j++)
+			xenbus_check_frontend(devclass[i], dev[j]);
+		kfree(dev);
+	}
+	kfree(devclass);
+}
+
+static int frontend_probe_and_watch(struct notifier_block *notifier,
+				   unsigned long event,
+				   void *data)
+{
+	/* reset devices in Connected or Closed state */
+	if (xen_hvm_domain())
+		xenbus_reset_state();
+	/* Enumerate devices in xenstore and watch for changes. */
+	xenbus_probe_devices(&xenbus_frontend);
+	register_xenbus_watch(&fe_watch);
+
+	return NOTIFY_DONE;
+}
+
+
+static int __init xenbus_probe_frontend_init(void)
+{
+	static struct notifier_block xenstore_notifier = {
+		.notifier_call = frontend_probe_and_watch
+	};
+	int err;
+
+	DPRINTK("");
+
+	/* Register ourselves with the kernel bus subsystem */
+	err = bus_register(&xenbus_frontend.bus);
+	if (err)
+		return err;
+
+	register_xenstore_notifier(&xenstore_notifier);
+
+	return 0;
+}
+subsys_initcall(xenbus_probe_frontend_init);
+
+#ifndef MODULE
+static int __init boot_wait_for_devices(void)
+{
+	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+		return -ENODEV;
+
+	ready_to_wait_for_devices = 1;
+	wait_for_devices(NULL);
+	return 0;
+}
+
+late_initcall(boot_wait_for_devices);
+#endif
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
new file mode 100644
index 00000000..d1c217b2
--- /dev/null
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -0,0 +1,904 @@
+/******************************************************************************
+ * xenbus_xs.c
+ *
+ * This is the kernel equivalent of the "xs" library.  We don't need everything
+ * and we use xenbus_comms for communication.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/unistd.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/uio.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/fcntl.h>
+#include <linux/kthread.h>
+#include <linux/rwsem.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <xen/xenbus.h>
+#include <xen/xen.h>
+#include "xenbus_comms.h"
+
+struct xs_stored_msg {
+	struct list_head list;
+
+	struct xsd_sockmsg hdr;
+
+	union {
+		/* Queued replies. */
+		struct {
+			char *body;
+		} reply;
+
+		/* Queued watch events. */
+		struct {
+			struct xenbus_watch *handle;
+			char **vec;
+			unsigned int vec_size;
+		} watch;
+	} u;
+};
+
+struct xs_handle {
+	/* A list of replies. Currently only one will ever be outstanding. */
+	struct list_head reply_list;
+	spinlock_t reply_lock;
+	wait_queue_head_t reply_waitq;
+
+	/*
+	 * Mutex ordering: transaction_mutex -> watch_mutex -> request_mutex.
+	 * response_mutex is never taken simultaneously with the other three.
+	 *
+	 * transaction_mutex must be held before incrementing
+	 * transaction_count. The mutex is held when a suspend is in
+	 * progress to prevent new transactions starting.
+	 *
+	 * When decrementing transaction_count to zero the wait queue
+	 * should be woken up, the suspend code waits for count to
+	 * reach zero.
+	 */
+
+	/* One request at a time. */
+	struct mutex request_mutex;
+
+	/* Protect xenbus reader thread against save/restore. */
+	struct mutex response_mutex;
+
+	/* Protect transactions against save/restore. */
+	struct mutex transaction_mutex;
+	atomic_t transaction_count;
+	wait_queue_head_t transaction_wq;
+
+	/* Protect watch (de)register against save/restore. */
+	struct rw_semaphore watch_mutex;
+};
+
+static struct xs_handle xs_state;
+
+/* List of registered watches, and a lock to protect it. */
+static LIST_HEAD(watches);
+static DEFINE_SPINLOCK(watches_lock);
+
+/* List of pending watch callback events, and a lock to protect it. */
+static LIST_HEAD(watch_events);
+static DEFINE_SPINLOCK(watch_events_lock);
+
+/*
+ * Details of the xenwatch callback kernel thread. The thread waits on the
+ * watch_events_waitq for work to do (queued on watch_events list). When it
+ * wakes up it acquires the xenwatch_mutex before reading the list and
+ * carrying out work.
+ */
+static pid_t xenwatch_pid;
+static DEFINE_MUTEX(xenwatch_mutex);
+static DECLARE_WAIT_QUEUE_HEAD(watch_events_waitq);
+
+static int get_error(const char *errorstring)
+{
+	unsigned int i;
+
+	for (i = 0; strcmp(errorstring, xsd_errors[i].errstring) != 0; i++) {
+		if (i == ARRAY_SIZE(xsd_errors) - 1) {
+			printk(KERN_WARNING
+			       "XENBUS xen store gave: unknown error %s",
+			       errorstring);
+			return EINVAL;
+		}
+	}
+	return xsd_errors[i].errnum;
+}
+
+static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
+{
+	struct xs_stored_msg *msg;
+	char *body;
+
+	spin_lock(&xs_state.reply_lock);
+
+	while (list_empty(&xs_state.reply_list)) {
+		spin_unlock(&xs_state.reply_lock);
+		/* XXX FIXME: Avoid synchronous wait for response here. */
+		wait_event(xs_state.reply_waitq,
+			   !list_empty(&xs_state.reply_list));
+		spin_lock(&xs_state.reply_lock);
+	}
+
+	msg = list_entry(xs_state.reply_list.next,
+			 struct xs_stored_msg, list);
+	list_del(&msg->list);
+
+	spin_unlock(&xs_state.reply_lock);
+
+	*type = msg->hdr.type;
+	if (len)
+		*len = msg->hdr.len;
+	body = msg->u.reply.body;
+
+	kfree(msg);
+
+	return body;
+}
+
+static void transaction_start(void)
+{
+	mutex_lock(&xs_state.transaction_mutex);
+	atomic_inc(&xs_state.transaction_count);
+	mutex_unlock(&xs_state.transaction_mutex);
+}
+
+static void transaction_end(void)
+{
+	if (atomic_dec_and_test(&xs_state.transaction_count))
+		wake_up(&xs_state.transaction_wq);
+}
+
+static void transaction_suspend(void)
+{
+	mutex_lock(&xs_state.transaction_mutex);
+	wait_event(xs_state.transaction_wq,
+		   atomic_read(&xs_state.transaction_count) == 0);
+}
+
+static void transaction_resume(void)
+{
+	mutex_unlock(&xs_state.transaction_mutex);
+}
+
+void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
+{
+	void *ret;
+	struct xsd_sockmsg req_msg = *msg;
+	int err;
+
+	if (req_msg.type == XS_TRANSACTION_START)
+		transaction_start();
+
+	mutex_lock(&xs_state.request_mutex);
+
+	err = xb_write(msg, sizeof(*msg) + msg->len);
+	if (err) {
+		msg->type = XS_ERROR;
+		ret = ERR_PTR(err);
+	} else
+		ret = read_reply(&msg->type, &msg->len);
+
+	mutex_unlock(&xs_state.request_mutex);
+
+	if ((msg->type == XS_TRANSACTION_END) ||
+	    ((req_msg.type == XS_TRANSACTION_START) &&
+	     (msg->type == XS_ERROR)))
+		transaction_end();
+
+	return ret;
+}
+EXPORT_SYMBOL(xenbus_dev_request_and_reply);
+
+/* Send message to xs, get kmalloc'ed reply.  ERR_PTR() on error. */
+static void *xs_talkv(struct xenbus_transaction t,
+		      enum xsd_sockmsg_type type,
+		      const struct kvec *iovec,
+		      unsigned int num_vecs,
+		      unsigned int *len)
+{
+	struct xsd_sockmsg msg;
+	void *ret = NULL;
+	unsigned int i;
+	int err;
+
+	msg.tx_id = t.id;
+	msg.req_id = 0;
+	msg.type = type;
+	msg.len = 0;
+	for (i = 0; i < num_vecs; i++)
+		msg.len += iovec[i].iov_len;
+
+	mutex_lock(&xs_state.request_mutex);
+
+	err = xb_write(&msg, sizeof(msg));
+	if (err) {
+		mutex_unlock(&xs_state.request_mutex);
+		return ERR_PTR(err);
+	}
+
+	for (i = 0; i < num_vecs; i++) {
+		err = xb_write(iovec[i].iov_base, iovec[i].iov_len);
+		if (err) {
+			mutex_unlock(&xs_state.request_mutex);
+			return ERR_PTR(err);
+		}
+	}
+
+	ret = read_reply(&msg.type, len);
+
+	mutex_unlock(&xs_state.request_mutex);
+
+	if (IS_ERR(ret))
+		return ret;
+
+	if (msg.type == XS_ERROR) {
+		err = get_error(ret);
+		kfree(ret);
+		return ERR_PTR(-err);
+	}
+
+	if (msg.type != type) {
+		if (printk_ratelimit())
+			printk(KERN_WARNING
+			       "XENBUS unexpected type [%d], expected [%d]\n",
+			       msg.type, type);
+		kfree(ret);
+		return ERR_PTR(-EINVAL);
+	}
+	return ret;
+}
+
+/* Simplified version of xs_talkv: single message. */
+static void *xs_single(struct xenbus_transaction t,
+		       enum xsd_sockmsg_type type,
+		       const char *string,
+		       unsigned int *len)
+{
+	struct kvec iovec;
+
+	iovec.iov_base = (void *)string;
+	iovec.iov_len = strlen(string) + 1;
+	return xs_talkv(t, type, &iovec, 1, len);
+}
+
+/* Many commands only need an ack, don't care what it says. */
+static int xs_error(char *reply)
+{
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+	kfree(reply);
+	return 0;
+}
+
+static unsigned int count_strings(const char *strings, unsigned int len)
+{
+	unsigned int num;
+	const char *p;
+
+	for (p = strings, num = 0; p < strings + len; p += strlen(p) + 1)
+		num++;
+
+	return num;
+}
+
+/* Return the path to dir with /name appended. Buffer must be kfree()'ed. */
+static char *join(const char *dir, const char *name)
+{
+	char *buffer;
+
+	if (strlen(name) == 0)
+		buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s", dir);
+	else
+		buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/%s", dir, name);
+	return (!buffer) ? ERR_PTR(-ENOMEM) : buffer;
+}
+
+static char **split(char *strings, unsigned int len, unsigned int *num)
+{
+	char *p, **ret;
+
+	/* Count the strings. */
+	*num = count_strings(strings, len);
+
+	/* Transfer to one big alloc for easy freeing. */
+	ret = kmalloc(*num * sizeof(char *) + len, GFP_NOIO | __GFP_HIGH);
+	if (!ret) {
+		kfree(strings);
+		return ERR_PTR(-ENOMEM);
+	}
+	memcpy(&ret[*num], strings, len);
+	kfree(strings);
+
+	strings = (char *)&ret[*num];
+	for (p = strings, *num = 0; p < strings + len; p += strlen(p) + 1)
+		ret[(*num)++] = p;
+
+	return ret;
+}
+
+char **xenbus_directory(struct xenbus_transaction t,
+			const char *dir, const char *node, unsigned int *num)
+{
+	char *strings, *path;
+	unsigned int len;
+
+	path = join(dir, node);
+	if (IS_ERR(path))
+		return (char **)path;
+
+	strings = xs_single(t, XS_DIRECTORY, path, &len);
+	kfree(path);
+	if (IS_ERR(strings))
+		return (char **)strings;
+
+	return split(strings, len, num);
+}
+EXPORT_SYMBOL_GPL(xenbus_directory);
+
+/* Check if a path exists. Return 1 if it does. */
+int xenbus_exists(struct xenbus_transaction t,
+		  const char *dir, const char *node)
+{
+	char **d;
+	int dir_n;
+
+	d = xenbus_directory(t, dir, node, &dir_n);
+	if (IS_ERR(d))
+		return 0;
+	kfree(d);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(xenbus_exists);
+
+/* Get the value of a single file.
+ * Returns a kmalloced value: call free() on it after use.
+ * len indicates length in bytes.
+ */
+void *xenbus_read(struct xenbus_transaction t,
+		  const char *dir, const char *node, unsigned int *len)
+{
+	char *path;
+	void *ret;
+
+	path = join(dir, node);
+	if (IS_ERR(path))
+		return (void *)path;
+
+	ret = xs_single(t, XS_READ, path, len);
+	kfree(path);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_read);
+
+/* Write the value of a single file.
+ * Returns -err on failure.
+ */
+int xenbus_write(struct xenbus_transaction t,
+		 const char *dir, const char *node, const char *string)
+{
+	const char *path;
+	struct kvec iovec[2];
+	int ret;
+
+	path = join(dir, node);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	iovec[0].iov_base = (void *)path;
+	iovec[0].iov_len = strlen(path) + 1;
+	iovec[1].iov_base = (void *)string;
+	iovec[1].iov_len = strlen(string);
+
+	ret = xs_error(xs_talkv(t, XS_WRITE, iovec, ARRAY_SIZE(iovec), NULL));
+	kfree(path);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_write);
+
+/* Create a new directory. */
+int xenbus_mkdir(struct xenbus_transaction t,
+		 const char *dir, const char *node)
+{
+	char *path;
+	int ret;
+
+	path = join(dir, node);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	ret = xs_error(xs_single(t, XS_MKDIR, path, NULL));
+	kfree(path);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_mkdir);
+
+/* Destroy a file or directory (directories must be empty). */
+int xenbus_rm(struct xenbus_transaction t, const char *dir, const char *node)
+{
+	char *path;
+	int ret;
+
+	path = join(dir, node);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	ret = xs_error(xs_single(t, XS_RM, path, NULL));
+	kfree(path);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_rm);
+
+/* Start a transaction: changes by others will not be seen during this
+ * transaction, and changes will not be visible to others until end.
+ */
+int xenbus_transaction_start(struct xenbus_transaction *t)
+{
+	char *id_str;
+
+	transaction_start();
+
+	id_str = xs_single(XBT_NIL, XS_TRANSACTION_START, "", NULL);
+	if (IS_ERR(id_str)) {
+		transaction_end();
+		return PTR_ERR(id_str);
+	}
+
+	t->id = simple_strtoul(id_str, NULL, 0);
+	kfree(id_str);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xenbus_transaction_start);
+
+/* End a transaction.
+ * If abandon is true, transaction is discarded instead of committed.
+ */
+int xenbus_transaction_end(struct xenbus_transaction t, int abort)
+{
+	char abortstr[2];
+	int err;
+
+	if (abort)
+		strcpy(abortstr, "F");
+	else
+		strcpy(abortstr, "T");
+
+	err = xs_error(xs_single(t, XS_TRANSACTION_END, abortstr, NULL));
+
+	transaction_end();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xenbus_transaction_end);
+
+/* Single read and scanf: returns -errno or num scanned. */
+int xenbus_scanf(struct xenbus_transaction t,
+		 const char *dir, const char *node, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+	char *val;
+
+	val = xenbus_read(t, dir, node, NULL);
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+
+	va_start(ap, fmt);
+	ret = vsscanf(val, fmt, ap);
+	va_end(ap);
+	kfree(val);
+	/* Distinctive errno. */
+	if (ret == 0)
+		return -ERANGE;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_scanf);
+
+/* Single printf and write: returns -errno or 0. */
+int xenbus_printf(struct xenbus_transaction t,
+		  const char *dir, const char *node, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+	char *buf;
+
+	va_start(ap, fmt);
+	buf = kvasprintf(GFP_NOIO | __GFP_HIGH, fmt, ap);
+	va_end(ap);
+
+	if (!buf)
+		return -ENOMEM;
+
+	ret = xenbus_write(t, dir, node, buf);
+
+	kfree(buf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_printf);
+
+/* Takes tuples of names, scanf-style args, and void **, NULL terminated. */
+int xenbus_gather(struct xenbus_transaction t, const char *dir, ...)
+{
+	va_list ap;
+	const char *name;
+	int ret = 0;
+
+	va_start(ap, dir);
+	while (ret == 0 && (name = va_arg(ap, char *)) != NULL) {
+		const char *fmt = va_arg(ap, char *);
+		void *result = va_arg(ap, void *);
+		char *p;
+
+		p = xenbus_read(t, dir, name, NULL);
+		if (IS_ERR(p)) {
+			ret = PTR_ERR(p);
+			break;
+		}
+		if (fmt) {
+			if (sscanf(p, fmt, result) == 0)
+				ret = -EINVAL;
+			kfree(p);
+		} else
+			*(char **)result = p;
+	}
+	va_end(ap);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xenbus_gather);
+
+static int xs_watch(const char *path, const char *token)
+{
+	struct kvec iov[2];
+
+	iov[0].iov_base = (void *)path;
+	iov[0].iov_len = strlen(path) + 1;
+	iov[1].iov_base = (void *)token;
+	iov[1].iov_len = strlen(token) + 1;
+
+	return xs_error(xs_talkv(XBT_NIL, XS_WATCH, iov,
+				 ARRAY_SIZE(iov), NULL));
+}
+
+static int xs_unwatch(const char *path, const char *token)
+{
+	struct kvec iov[2];
+
+	iov[0].iov_base = (char *)path;
+	iov[0].iov_len = strlen(path) + 1;
+	iov[1].iov_base = (char *)token;
+	iov[1].iov_len = strlen(token) + 1;
+
+	return xs_error(xs_talkv(XBT_NIL, XS_UNWATCH, iov,
+				 ARRAY_SIZE(iov), NULL));
+}
+
+static struct xenbus_watch *find_watch(const char *token)
+{
+	struct xenbus_watch *i, *cmp;
+
+	cmp = (void *)simple_strtoul(token, NULL, 16);
+
+	list_for_each_entry(i, &watches, list)
+		if (i == cmp)
+			return i;
+
+	return NULL;
+}
+
+/* Register callback to watch this node. */
+int register_xenbus_watch(struct xenbus_watch *watch)
+{
+	/* Pointer in ascii is the token. */
+	char token[sizeof(watch) * 2 + 1];
+	int err;
+
+	sprintf(token, "%lX", (long)watch);
+
+	down_read(&xs_state.watch_mutex);
+
+	spin_lock(&watches_lock);
+	BUG_ON(find_watch(token));
+	list_add(&watch->list, &watches);
+	spin_unlock(&watches_lock);
+
+	err = xs_watch(watch->node, token);
+
+	if (err) {
+		spin_lock(&watches_lock);
+		list_del(&watch->list);
+		spin_unlock(&watches_lock);
+	}
+
+	up_read(&xs_state.watch_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_xenbus_watch);
+
+void unregister_xenbus_watch(struct xenbus_watch *watch)
+{
+	struct xs_stored_msg *msg, *tmp;
+	char token[sizeof(watch) * 2 + 1];
+	int err;
+
+	sprintf(token, "%lX", (long)watch);
+
+	down_read(&xs_state.watch_mutex);
+
+	spin_lock(&watches_lock);
+	BUG_ON(!find_watch(token));
+	list_del(&watch->list);
+	spin_unlock(&watches_lock);
+
+	err = xs_unwatch(watch->node, token);
+	if (err)
+		printk(KERN_WARNING
+		       "XENBUS Failed to release watch %s: %i\n",
+		       watch->node, err);
+
+	up_read(&xs_state.watch_mutex);
+
+	/* Make sure there are no callbacks running currently (unless
+	   its us) */
+	if (current->pid != xenwatch_pid)
+		mutex_lock(&xenwatch_mutex);
+
+	/* Cancel pending watch events. */
+	spin_lock(&watch_events_lock);
+	list_for_each_entry_safe(msg, tmp, &watch_events, list) {
+		if (msg->u.watch.handle != watch)
+			continue;
+		list_del(&msg->list);
+		kfree(msg->u.watch.vec);
+		kfree(msg);
+	}
+	spin_unlock(&watch_events_lock);
+
+	if (current->pid != xenwatch_pid)
+		mutex_unlock(&xenwatch_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_xenbus_watch);
+
+void xs_suspend(void)
+{
+	transaction_suspend();
+	down_write(&xs_state.watch_mutex);
+	mutex_lock(&xs_state.request_mutex);
+	mutex_lock(&xs_state.response_mutex);
+}
+
+void xs_resume(void)
+{
+	struct xenbus_watch *watch;
+	char token[sizeof(watch) * 2 + 1];
+
+	xb_init_comms();
+
+	mutex_unlock(&xs_state.response_mutex);
+	mutex_unlock(&xs_state.request_mutex);
+	transaction_resume();
+
+	/* No need for watches_lock: the watch_mutex is sufficient. */
+	list_for_each_entry(watch, &watches, list) {
+		sprintf(token, "%lX", (long)watch);
+		xs_watch(watch->node, token);
+	}
+
+	up_write(&xs_state.watch_mutex);
+}
+
+void xs_suspend_cancel(void)
+{
+	mutex_unlock(&xs_state.response_mutex);
+	mutex_unlock(&xs_state.request_mutex);
+	up_write(&xs_state.watch_mutex);
+	mutex_unlock(&xs_state.transaction_mutex);
+}
+
+static int xenwatch_thread(void *unused)
+{
+	struct list_head *ent;
+	struct xs_stored_msg *msg;
+
+	for (;;) {
+		wait_event_interruptible(watch_events_waitq,
+					 !list_empty(&watch_events));
+
+		if (kthread_should_stop())
+			break;
+
+		mutex_lock(&xenwatch_mutex);
+
+		spin_lock(&watch_events_lock);
+		ent = watch_events.next;
+		if (ent != &watch_events)
+			list_del(ent);
+		spin_unlock(&watch_events_lock);
+
+		if (ent != &watch_events) {
+			msg = list_entry(ent, struct xs_stored_msg, list);
+			msg->u.watch.handle->callback(
+				msg->u.watch.handle,
+				(const char **)msg->u.watch.vec,
+				msg->u.watch.vec_size);
+			kfree(msg->u.watch.vec);
+			kfree(msg);
+		}
+
+		mutex_unlock(&xenwatch_mutex);
+	}
+
+	return 0;
+}
+
+static int process_msg(void)
+{
+	struct xs_stored_msg *msg;
+	char *body;
+	int err;
+
+	/*
+	 * We must disallow save/restore while reading a xenstore message.
+	 * A partial read across s/r leaves us out of sync with xenstored.
+	 */
+	for (;;) {
+		err = xb_wait_for_data_to_read();
+		if (err)
+			return err;
+		mutex_lock(&xs_state.response_mutex);
+		if (xb_data_to_read())
+			break;
+		/* We raced with save/restore: pending data 'disappeared'. */
+		mutex_unlock(&xs_state.response_mutex);
+	}
+
+
+	msg = kmalloc(sizeof(*msg), GFP_NOIO | __GFP_HIGH);
+	if (msg == NULL) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = xb_read(&msg->hdr, sizeof(msg->hdr));
+	if (err) {
+		kfree(msg);
+		goto out;
+	}
+
+	if (msg->hdr.len > XENSTORE_PAYLOAD_MAX) {
+		kfree(msg);
+		err = -EINVAL;
+		goto out;
+	}
+
+	body = kmalloc(msg->hdr.len + 1, GFP_NOIO | __GFP_HIGH);
+	if (body == NULL) {
+		kfree(msg);
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = xb_read(body, msg->hdr.len);
+	if (err) {
+		kfree(body);
+		kfree(msg);
+		goto out;
+	}
+	body[msg->hdr.len] = '\0';
+
+	if (msg->hdr.type == XS_WATCH_EVENT) {
+		msg->u.watch.vec = split(body, msg->hdr.len,
+					 &msg->u.watch.vec_size);
+		if (IS_ERR(msg->u.watch.vec)) {
+			err = PTR_ERR(msg->u.watch.vec);
+			kfree(msg);
+			goto out;
+		}
+
+		spin_lock(&watches_lock);
+		msg->u.watch.handle = find_watch(
+			msg->u.watch.vec[XS_WATCH_TOKEN]);
+		if (msg->u.watch.handle != NULL) {
+			spin_lock(&watch_events_lock);
+			list_add_tail(&msg->list, &watch_events);
+			wake_up(&watch_events_waitq);
+			spin_unlock(&watch_events_lock);
+		} else {
+			kfree(msg->u.watch.vec);
+			kfree(msg);
+		}
+		spin_unlock(&watches_lock);
+	} else {
+		msg->u.reply.body = body;
+		spin_lock(&xs_state.reply_lock);
+		list_add_tail(&msg->list, &xs_state.reply_list);
+		spin_unlock(&xs_state.reply_lock);
+		wake_up(&xs_state.reply_waitq);
+	}
+
+ out:
+	mutex_unlock(&xs_state.response_mutex);
+	return err;
+}
+
+static int xenbus_thread(void *unused)
+{
+	int err;
+
+	for (;;) {
+		err = process_msg();
+		if (err)
+			printk(KERN_WARNING "XENBUS error %d while reading "
+			       "message\n", err);
+		if (kthread_should_stop())
+			break;
+	}
+
+	return 0;
+}
+
+int xs_init(void)
+{
+	int err;
+	struct task_struct *task;
+
+	INIT_LIST_HEAD(&xs_state.reply_list);
+	spin_lock_init(&xs_state.reply_lock);
+	init_waitqueue_head(&xs_state.reply_waitq);
+
+	mutex_init(&xs_state.request_mutex);
+	mutex_init(&xs_state.response_mutex);
+	mutex_init(&xs_state.transaction_mutex);
+	init_rwsem(&xs_state.watch_mutex);
+	atomic_set(&xs_state.transaction_count, 0);
+	init_waitqueue_head(&xs_state.transaction_wq);
+
+	/* Initialize the shared memory rings to talk to xenstored */
+	err = xb_init_comms();
+	if (err)
+		return err;
+
+	task = kthread_run(xenwatch_thread, NULL, "xenwatch");
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	xenwatch_pid = task->pid;
+
+	task = kthread_run(xenbus_thread, NULL, "xenbus");
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
+	return 0;
+}
diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c
new file mode 100644
index 00000000..b91f8ff5
--- /dev/null
+++ b/drivers/xen/xencomm.c
@@ -0,0 +1,217 @@
+/*
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ * Copyright (C) IBM Corp. 2006
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/page.h>
+#include <xen/xencomm.h>
+#include <xen/interface/xen.h>
+#include <asm/xen/xencomm.h>	/* for xencomm_is_phys_contiguous() */
+
+static int xencomm_init(struct xencomm_desc *desc,
+			void *buffer, unsigned long bytes)
+{
+	unsigned long recorded = 0;
+	int i = 0;
+
+	while ((recorded < bytes) && (i < desc->nr_addrs)) {
+		unsigned long vaddr = (unsigned long)buffer + recorded;
+		unsigned long paddr;
+		int offset;
+		int chunksz;
+
+		offset = vaddr % PAGE_SIZE; /* handle partial pages */
+		chunksz = min(PAGE_SIZE - offset, bytes - recorded);
+
+		paddr = xencomm_vtop(vaddr);
+		if (paddr == ~0UL) {
+			printk(KERN_DEBUG "%s: couldn't translate vaddr %lx\n",
+			       __func__, vaddr);
+			return -EINVAL;
+		}
+
+		desc->address[i++] = paddr;
+		recorded += chunksz;
+	}
+
+	if (recorded < bytes) {
+		printk(KERN_DEBUG
+		       "%s: could only translate %ld of %ld bytes\n",
+		       __func__, recorded, bytes);
+		return -ENOSPC;
+	}
+
+	/* mark remaining addresses invalid (just for safety) */
+	while (i < desc->nr_addrs)
+		desc->address[i++] = XENCOMM_INVALID;
+
+	desc->magic = XENCOMM_MAGIC;
+
+	return 0;
+}
+
+static struct xencomm_desc *xencomm_alloc(gfp_t gfp_mask,
+					  void *buffer, unsigned long bytes)
+{
+	struct xencomm_desc *desc;
+	unsigned long buffer_ulong = (unsigned long)buffer;
+	unsigned long start = buffer_ulong & PAGE_MASK;
+	unsigned long end = (buffer_ulong + bytes) | ~PAGE_MASK;
+	unsigned long nr_addrs = (end - start + 1) >> PAGE_SHIFT;
+	unsigned long size = sizeof(*desc) +
+		sizeof(desc->address[0]) * nr_addrs;
+
+	/*
+	 * slab allocator returns at least sizeof(void*) aligned pointer.
+	 * When sizeof(*desc) > sizeof(void*), struct xencomm_desc might
+	 * cross page boundary.
+	 */
+	if (sizeof(*desc) > sizeof(void *)) {
+		unsigned long order = get_order(size);
+		desc = (struct xencomm_desc *)__get_free_pages(gfp_mask,
+							       order);
+		if (desc == NULL)
+			return NULL;
+
+		desc->nr_addrs =
+			((PAGE_SIZE << order) - sizeof(struct xencomm_desc)) /
+			sizeof(*desc->address);
+	} else {
+		desc = kmalloc(size, gfp_mask);
+		if (desc == NULL)
+			return NULL;
+
+		desc->nr_addrs = nr_addrs;
+	}
+	return desc;
+}
+
+void xencomm_free(struct xencomm_handle *desc)
+{
+	if (desc && !((ulong)desc & XENCOMM_INLINE_FLAG)) {
+		struct xencomm_desc *desc__ = (struct xencomm_desc *)desc;
+		if (sizeof(*desc__) > sizeof(void *)) {
+			unsigned long size = sizeof(*desc__) +
+				sizeof(desc__->address[0]) * desc__->nr_addrs;
+			unsigned long order = get_order(size);
+			free_pages((unsigned long)__va(desc), order);
+		} else
+			kfree(__va(desc));
+	}
+}
+
+static int xencomm_create(void *buffer, unsigned long bytes,
+			  struct xencomm_desc **ret, gfp_t gfp_mask)
+{
+	struct xencomm_desc *desc;
+	int rc;
+
+	pr_debug("%s: %p[%ld]\n", __func__, buffer, bytes);
+
+	if (bytes == 0) {
+		/* don't create a descriptor; Xen recognizes NULL. */
+		BUG_ON(buffer != NULL);
+		*ret = NULL;
+		return 0;
+	}
+
+	BUG_ON(buffer == NULL); /* 'bytes' is non-zero */
+
+	desc = xencomm_alloc(gfp_mask, buffer, bytes);
+	if (!desc) {
+		printk(KERN_DEBUG "%s failure\n", "xencomm_alloc");
+		return -ENOMEM;
+	}
+
+	rc = xencomm_init(desc, buffer, bytes);
+	if (rc) {
+		printk(KERN_DEBUG "%s failure: %d\n", "xencomm_init", rc);
+		xencomm_free((struct xencomm_handle *)__pa(desc));
+		return rc;
+	}
+
+	*ret = desc;
+	return 0;
+}
+
+static struct xencomm_handle *xencomm_create_inline(void *ptr)
+{
+	unsigned long paddr;
+
+	BUG_ON(!xencomm_is_phys_contiguous((unsigned long)ptr));
+
+	paddr = (unsigned long)xencomm_pa(ptr);
+	BUG_ON(paddr & XENCOMM_INLINE_FLAG);
+	return (struct xencomm_handle *)(paddr | XENCOMM_INLINE_FLAG);
+}
+
+/* "mini" routine, for stack-based communications: */
+static int xencomm_create_mini(void *buffer,
+	unsigned long bytes, struct xencomm_mini *xc_desc,
+	struct xencomm_desc **ret)
+{
+	int rc = 0;
+	struct xencomm_desc *desc;
+	BUG_ON(((unsigned long)xc_desc) % sizeof(*xc_desc) != 0);
+
+	desc = (void *)xc_desc;
+
+	desc->nr_addrs = XENCOMM_MINI_ADDRS;
+
+	rc = xencomm_init(desc, buffer, bytes);
+	if (!rc)
+		*ret = desc;
+
+	return rc;
+}
+
+struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes)
+{
+	int rc;
+	struct xencomm_desc *desc;
+
+	if (xencomm_is_phys_contiguous((unsigned long)ptr))
+		return xencomm_create_inline(ptr);
+
+	rc = xencomm_create(ptr, bytes, &desc, GFP_KERNEL);
+
+	if (rc || desc == NULL)
+		return NULL;
+
+	return xencomm_pa(desc);
+}
+
+struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, unsigned long bytes,
+			struct xencomm_mini *xc_desc)
+{
+	int rc;
+	struct xencomm_desc *desc = NULL;
+
+	if (xencomm_is_phys_contiguous((unsigned long)ptr))
+		return xencomm_create_inline(ptr);
+
+	rc = xencomm_create_mini(ptr, bytes, xc_desc,
+				&desc);
+
+	if (rc)
+		return NULL;
+
+	return xencomm_pa(desc);
+}
diff --git a/drivers/xen/xenfs/Makefile b/drivers/xen/xenfs/Makefile
new file mode 100644
index 00000000..b019865f
--- /dev/null
+++ b/drivers/xen/xenfs/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_XENFS) += xenfs.o
+
+xenfs-y			  = super.o
+xenfs-$(CONFIG_XEN_DOM0) += xenstored.o
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
new file mode 100644
index 00000000..a84b53c0
--- /dev/null
+++ b/drivers/xen/xenfs/super.c
@@ -0,0 +1,139 @@
+/*
+ *  xenfs.c - a filesystem for passing info between the a domain and
+ *  the hypervisor.
+ *
+ * 2008-10-07  Alex Zeffertt    Replaced /proc/xen/xenbus with xenfs filesystem
+ *                              and /proc/xen compatibility mount point.
+ *                              Turned xenfs into a loadable module.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/magic.h>
+
+#include <xen/xen.h>
+
+#include "xenfs.h"
+#include "../privcmd.h"
+#include "../xenbus/xenbus_comms.h"
+
+#include <asm/xen/hypervisor.h>
+
+MODULE_DESCRIPTION("Xen filesystem");
+MODULE_LICENSE("GPL");
+
+static struct inode *xenfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret = new_inode(sb);
+
+	if (ret) {
+		ret->i_mode = mode;
+		ret->i_uid = ret->i_gid = 0;
+		ret->i_blocks = 0;
+		ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
+	}
+	return ret;
+}
+
+static struct dentry *xenfs_create_file(struct super_block *sb,
+					struct dentry *parent,
+					const char *name,
+					const struct file_operations *fops,
+					void *data,
+					int mode)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(parent, name);
+	if (!dentry)
+		return NULL;
+
+	inode = xenfs_make_inode(sb, S_IFREG | mode);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+
+	inode->i_fop = fops;
+	inode->i_private = data;
+
+	d_add(dentry, inode);
+	return dentry;
+}
+
+static ssize_t capabilities_read(struct file *file, char __user *buf,
+				 size_t size, loff_t *off)
+{
+	char *tmp = "";
+
+	if (xen_initial_domain())
+		tmp = "control_d\n";
+
+	return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
+}
+
+static const struct file_operations capabilities_file_ops = {
+	.read = capabilities_read,
+	.llseek = default_llseek,
+};
+
+static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	static struct tree_descr xenfs_files[] = {
+		[1] = {},
+		{ "xenbus", &xen_xenbus_fops, S_IRUSR|S_IWUSR },
+		{ "capabilities", &capabilities_file_ops, S_IRUGO },
+		{ "privcmd", &xen_privcmd_fops, S_IRUSR|S_IWUSR },
+		{""},
+	};
+	int rc;
+
+	rc = simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files);
+	if (rc < 0)
+		return rc;
+
+	if (xen_initial_domain()) {
+		xenfs_create_file(sb, sb->s_root, "xsd_kva",
+				  &xsd_kva_file_ops, NULL, S_IRUSR|S_IWUSR);
+		xenfs_create_file(sb, sb->s_root, "xsd_port",
+				  &xsd_port_file_ops, NULL, S_IRUSR|S_IWUSR);
+	}
+
+	return rc;
+}
+
+static struct dentry *xenfs_mount(struct file_system_type *fs_type,
+				  int flags, const char *dev_name,
+				  void *data)
+{
+	return mount_single(fs_type, flags, data, xenfs_fill_super);
+}
+
+static struct file_system_type xenfs_type = {
+	.owner =	THIS_MODULE,
+	.name =		"xenfs",
+	.mount =	xenfs_mount,
+	.kill_sb =	kill_litter_super,
+};
+
+static int __init xenfs_init(void)
+{
+	if (xen_domain())
+		return register_filesystem(&xenfs_type);
+
+	printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n");
+	return 0;
+}
+
+static void __exit xenfs_exit(void)
+{
+	if (xen_domain())
+		unregister_filesystem(&xenfs_type);
+}
+
+module_init(xenfs_init);
+module_exit(xenfs_exit);
+
diff --git a/drivers/xen/xenfs/xenfs.h b/drivers/xen/xenfs/xenfs.h
new file mode 100644
index 00000000..6b80c777
--- /dev/null
+++ b/drivers/xen/xenfs/xenfs.h
@@ -0,0 +1,7 @@
+#ifndef _XENFS_XENBUS_H
+#define _XENFS_XENBUS_H
+
+extern const struct file_operations xsd_kva_file_ops;
+extern const struct file_operations xsd_port_file_ops;
+
+#endif	/* _XENFS_XENBUS_H */
diff --git a/drivers/xen/xenfs/xenstored.c b/drivers/xen/xenfs/xenstored.c
new file mode 100644
index 00000000..fef20dbc
--- /dev/null
+++ b/drivers/xen/xenfs/xenstored.c
@@ -0,0 +1,68 @@
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+
+#include <xen/page.h>
+
+#include "xenfs.h"
+#include "../xenbus/xenbus_comms.h"
+
+static ssize_t xsd_read(struct file *file, char __user *buf,
+			    size_t size, loff_t *off)
+{
+	const char *str = (const char *)file->private_data;
+	return simple_read_from_buffer(buf, size, off, str, strlen(str));
+}
+
+static int xsd_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static int xsd_kva_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "0x%p",
+					       xen_store_interface);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+static int xsd_kva_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+
+	if ((size > PAGE_SIZE) || (vma->vm_pgoff != 0))
+		return -EINVAL;
+
+	if (remap_pfn_range(vma, vma->vm_start,
+			    virt_to_pfn(xen_store_interface),
+			    size, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+const struct file_operations xsd_kva_file_ops = {
+	.open = xsd_kva_open,
+	.mmap = xsd_kva_mmap,
+	.read = xsd_read,
+	.release = xsd_release,
+};
+
+static int xsd_port_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "%d",
+					       xen_store_evtchn);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+const struct file_operations xsd_port_file_ops = {
+	.open = xsd_port_open,
+	.read = xsd_read,
+	.release = xsd_release,
+};