Add the rt linux 4.1.3-rt3 as base

Import the rt linux 4.1.3-rt3 as OPNFV kvm base.

It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:

commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date:   Sat Jul 25 12:13:34 2015 +0200

    Prepare v4.1.3-rt3

    Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.

Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>

28 files changed, 5649 insertions, 0 deletions

diff --git a/kernel/include/xen/interface/callback.h b/kernel/include/xen/interface/callback.h
new file mode 100644
index 000000000..dc3193f4b
--- /dev/null
+++ b/kernel/include/xen/interface/callback.h
@@ -0,0 +1,102 @@
+/******************************************************************************
+ * callback.h
+ *
+ * Register guest OS callbacks with Xen.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2006, Ian Campbell
+ */
+
+#ifndef __XEN_PUBLIC_CALLBACK_H__
+#define __XEN_PUBLIC_CALLBACK_H__
+
+#include <xen/interface/xen.h>
+
+/*
+ * Prototype for this hypercall is:
+ *   long callback_op(int cmd, void *extra_args)
+ * @cmd        == CALLBACKOP_??? (callback operation).
+ * @extra_args == Operation-specific extra arguments (NULL if none).
+ */
+
+/* x86: Callback for event delivery. */
+#define CALLBACKTYPE_event                 0
+
+/* x86: Failsafe callback when guest state cannot be restored by Xen. */
+#define CALLBACKTYPE_failsafe              1
+
+/* x86/64 hypervisor: Syscall by 64-bit guest app ('64-on-64-on-64'). */
+#define CALLBACKTYPE_syscall               2
+
+/*
+ * x86/32 hypervisor: Only available on x86/32 when supervisor_mode_kernel
+ *     feature is enabled. Do not use this callback type in new code.
+ */
+#define CALLBACKTYPE_sysenter_deprecated   3
+
+/* x86: Callback for NMI delivery. */
+#define CALLBACKTYPE_nmi                   4
+
+/*
+ * x86: sysenter is only available as follows:
+ * - 32-bit hypervisor: with the supervisor_mode_kernel feature enabled
+ * - 64-bit hypervisor: 32-bit guest applications on Intel CPUs
+ *                      ('32-on-32-on-64', '32-on-64-on-64')
+ *                      [nb. also 64-bit guest applications on Intel CPUs
+ *                           ('64-on-64-on-64'), but syscall is preferred]
+ */
+#define CALLBACKTYPE_sysenter              5
+
+/*
+ * x86/64 hypervisor: Syscall by 32-bit guest app on AMD CPUs
+ *                    ('32-on-32-on-64', '32-on-64-on-64')
+ */
+#define CALLBACKTYPE_syscall32             7
+
+/*
+ * Disable event deliver during callback? This flag is ignored for event and
+ * NMI callbacks: event delivery is unconditionally disabled.
+ */
+#define _CALLBACKF_mask_events             0
+#define CALLBACKF_mask_events              (1U << _CALLBACKF_mask_events)
+
+/*
+ * Register a callback.
+ */
+#define CALLBACKOP_register                0
+struct callback_register {
+	uint16_t type;
+	uint16_t flags;
+	xen_callback_t address;
+};
+
+/*
+ * Unregister a callback.
+ *
+ * Not all callbacks can be unregistered. -EINVAL will be returned if
+ * you attempt to unregister such a callback.
+ */
+#define CALLBACKOP_unregister              1
+struct callback_unregister {
+    uint16_t type;
+    uint16_t _unused;
+};
+
+#endif /* __XEN_PUBLIC_CALLBACK_H__ */
diff --git a/kernel/include/xen/interface/elfnote.h b/kernel/include/xen/interface/elfnote.h
new file mode 100644
index 000000000..f90b03454
--- /dev/null
+++ b/kernel/include/xen/interface/elfnote.h
@@ -0,0 +1,210 @@
+/******************************************************************************
+ * elfnote.h
+ *
+ * Definitions used for the Xen ELF notes.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2006, Ian Campbell, XenSource Ltd.
+ */
+
+#ifndef __XEN_PUBLIC_ELFNOTE_H__
+#define __XEN_PUBLIC_ELFNOTE_H__
+
+/*
+ * The notes should live in a SHT_NOTE segment and have "Xen" in the
+ * name field.
+ *
+ * Numeric types are either 4 or 8 bytes depending on the content of
+ * the desc field.
+ *
+ * LEGACY indicated the fields in the legacy __xen_guest string which
+ * this a note type replaces.
+ *
+ * String values (for non-legacy) are NULL terminated ASCII, also known
+ * as ASCIZ type.
+ */
+
+/*
+ * NAME=VALUE pair (string).
+ */
+#define XEN_ELFNOTE_INFO           0
+
+/*
+ * The virtual address of the entry point (numeric).
+ *
+ * LEGACY: VIRT_ENTRY
+ */
+#define XEN_ELFNOTE_ENTRY          1
+
+/* The virtual address of the hypercall transfer page (numeric).
+ *
+ * LEGACY: HYPERCALL_PAGE. (n.b. legacy value is a physical page
+ * number not a virtual address)
+ */
+#define XEN_ELFNOTE_HYPERCALL_PAGE 2
+
+/* The virtual address where the kernel image should be mapped (numeric).
+ *
+ * Defaults to 0.
+ *
+ * LEGACY: VIRT_BASE
+ */
+#define XEN_ELFNOTE_VIRT_BASE      3
+
+/*
+ * The offset of the ELF paddr field from the acutal required
+ * pseudo-physical address (numeric).
+ *
+ * This is used to maintain backwards compatibility with older kernels
+ * which wrote __PAGE_OFFSET into that field. This field defaults to 0
+ * if not present.
+ *
+ * LEGACY: ELF_PADDR_OFFSET. (n.b. legacy default is VIRT_BASE)
+ */
+#define XEN_ELFNOTE_PADDR_OFFSET   4
+
+/*
+ * The version of Xen that we work with (string).
+ *
+ * LEGACY: XEN_VER
+ */
+#define XEN_ELFNOTE_XEN_VERSION    5
+
+/*
+ * The name of the guest operating system (string).
+ *
+ * LEGACY: GUEST_OS
+ */
+#define XEN_ELFNOTE_GUEST_OS       6
+
+/*
+ * The version of the guest operating system (string).
+ *
+ * LEGACY: GUEST_VER
+ */
+#define XEN_ELFNOTE_GUEST_VERSION  7
+
+/*
+ * The loader type (string).
+ *
+ * LEGACY: LOADER
+ */
+#define XEN_ELFNOTE_LOADER         8
+
+/*
+ * The kernel supports PAE (x86/32 only, string = "yes" or "no").
+ *
+ * LEGACY: PAE (n.b. The legacy interface included a provision to
+ * indicate 'extended-cr3' support allowing L3 page tables to be
+ * placed above 4G. It is assumed that any kernel new enough to use
+ * these ELF notes will include this and therefore "yes" here is
+ * equivalent to "yes[entended-cr3]" in the __xen_guest interface.
+ */
+#define XEN_ELFNOTE_PAE_MODE       9
+
+/*
+ * The features supported/required by this kernel (string).
+ *
+ * The string must consist of a list of feature names (as given in
+ * features.h, without the "XENFEAT_" prefix) separated by '|'
+ * characters. If a feature is required for the kernel to function
+ * then the feature name must be preceded by a '!' character.
+ *
+ * LEGACY: FEATURES
+ */
+#define XEN_ELFNOTE_FEATURES      10
+
+/*
+ * The kernel requires the symbol table to be loaded (string = "yes" or "no")
+ * LEGACY: BSD_SYMTAB (n.b. The legacy treated the presence or absence
+ * of this string as a boolean flag rather than requiring "yes" or
+ * "no".
+ */
+#define XEN_ELFNOTE_BSD_SYMTAB    11
+
+/*
+ * The lowest address the hypervisor hole can begin at (numeric).
+ *
+ * This must not be set higher than HYPERVISOR_VIRT_START. Its presence
+ * also indicates to the hypervisor that the kernel can deal with the
+ * hole starting at a higher address.
+ */
+#define XEN_ELFNOTE_HV_START_LOW  12
+
+/*
+ * List of maddr_t-sized mask/value pairs describing how to recognize
+ * (non-present) L1 page table entries carrying valid MFNs (numeric).
+ */
+#define XEN_ELFNOTE_L1_MFN_VALID  13
+
+/*
+ * Whether or not the guest supports cooperative suspend cancellation.
+ * This is a numeric value.
+ *
+ * Default is 0
+ */
+#define XEN_ELFNOTE_SUSPEND_CANCEL 14
+
+/*
+ * The (non-default) location the initial phys-to-machine map should be
+ * placed at by the hypervisor (Dom0) or the tools (DomU).
+ * The kernel must be prepared for this mapping to be established using
+ * large pages, despite such otherwise not being available to guests.
+ * The kernel must also be able to handle the page table pages used for
+ * this mapping not being accessible through the initial mapping.
+ * (Only x86-64 supports this at present.)
+ */
+#define XEN_ELFNOTE_INIT_P2M      15
+
+/*
+ * Whether or not the guest can deal with being passed an initrd not
+ * mapped through its initial page tables.
+ */
+#define XEN_ELFNOTE_MOD_START_PFN 16
+
+/*
+ * The features supported by this kernel (numeric).
+ *
+ * Other than XEN_ELFNOTE_FEATURES on pre-4.2 Xen, this note allows a
+ * kernel to specify support for features that older hypervisors don't
+ * know about. The set of features 4.2 and newer hypervisors will
+ * consider supported by the kernel is the combination of the sets
+ * specified through this and the string note.
+ *
+ * LEGACY: FEATURES
+ */
+#define XEN_ELFNOTE_SUPPORTED_FEATURES 17
+
+/*
+ * The number of the highest elfnote defined.
+ */
+#define XEN_ELFNOTE_MAX XEN_ELFNOTE_SUPPORTED_FEATURES
+
+#endif /* __XEN_PUBLIC_ELFNOTE_H__ */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-set-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/kernel/include/xen/interface/event_channel.h b/kernel/include/xen/interface/event_channel.h
new file mode 100644
index 000000000..7e6acef54
--- /dev/null
+++ b/kernel/include/xen/interface/event_channel.h
@@ -0,0 +1,278 @@
+/******************************************************************************
+ * event_channel.h
+ *
+ * Event channels between domains.
+ *
+ * Copyright (c) 2003-2004, K A Fraser.
+ */
+
+#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
+#define __XEN_PUBLIC_EVENT_CHANNEL_H__
+
+#include <xen/interface/xen.h>
+
+typedef uint32_t evtchn_port_t;
+DEFINE_GUEST_HANDLE(evtchn_port_t);
+
+/*
+ * EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as
+ * accepting interdomain bindings from domain <remote_dom>. A fresh port
+ * is allocated in <dom> and returned as <port>.
+ * NOTES:
+ *  1. If the caller is unprivileged then <dom> must be DOMID_SELF.
+ *  2. <rdom> may be DOMID_SELF, allowing loopback connections.
+ */
+#define EVTCHNOP_alloc_unbound	  6
+struct evtchn_alloc_unbound {
+	/* IN parameters */
+	domid_t dom, remote_dom;
+	/* OUT parameters */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between
+ * the calling domain and <remote_dom>. <remote_dom,remote_port> must identify
+ * a port that is unbound and marked as accepting bindings from the calling
+ * domain. A fresh port is allocated in the calling domain and returned as
+ * <local_port>.
+ * NOTES:
+ *  2. <remote_dom> may be DOMID_SELF, allowing loopback connections.
+ */
+#define EVTCHNOP_bind_interdomain 0
+struct evtchn_bind_interdomain {
+	/* IN parameters. */
+	domid_t remote_dom;
+	evtchn_port_t remote_port;
+	/* OUT parameters. */
+	evtchn_port_t local_port;
+};
+
+/*
+ * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified
+ * vcpu.
+ * NOTES:
+ *  1. A virtual IRQ may be bound to at most one event channel per vcpu.
+ *  2. The allocated event channel is bound to the specified vcpu. The binding
+ *     may not be changed.
+ */
+#define EVTCHNOP_bind_virq	  1
+struct evtchn_bind_virq {
+	/* IN parameters. */
+	uint32_t virq;
+	uint32_t vcpu;
+	/* OUT parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_bind_pirq: Bind a local event channel to PIRQ <irq>.
+ * NOTES:
+ *  1. A physical IRQ may be bound to at most one event channel per domain.
+ *  2. Only a sufficiently-privileged domain may bind to a physical IRQ.
+ */
+#define EVTCHNOP_bind_pirq	  2
+struct evtchn_bind_pirq {
+	/* IN parameters. */
+	uint32_t pirq;
+#define BIND_PIRQ__WILL_SHARE 1
+	uint32_t flags; /* BIND_PIRQ__* */
+	/* OUT parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_bind_ipi: Bind a local event channel to receive events.
+ * NOTES:
+ *  1. The allocated event channel is bound to the specified vcpu. The binding
+ *     may not be changed.
+ */
+#define EVTCHNOP_bind_ipi	  7
+struct evtchn_bind_ipi {
+	uint32_t vcpu;
+	/* OUT parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_close: Close a local event channel <port>. If the channel is
+ * interdomain then the remote end is placed in the unbound state
+ * (EVTCHNSTAT_unbound), awaiting a new connection.
+ */
+#define EVTCHNOP_close		  3
+struct evtchn_close {
+	/* IN parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_send: Send an event to the remote end of the channel whose local
+ * endpoint is <port>.
+ */
+#define EVTCHNOP_send		  4
+struct evtchn_send {
+	/* IN parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_status: Get the current status of the communication channel which
+ * has an endpoint at <dom, port>.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may obtain the status of an event
+ *     channel for which <dom> is not DOMID_SELF.
+ */
+#define EVTCHNOP_status		  5
+struct evtchn_status {
+	/* IN parameters */
+	domid_t  dom;
+	evtchn_port_t port;
+	/* OUT parameters */
+#define EVTCHNSTAT_closed	0  /* Channel is not in use.		     */
+#define EVTCHNSTAT_unbound	1  /* Channel is waiting interdom connection.*/
+#define EVTCHNSTAT_interdomain	2  /* Channel is connected to remote domain. */
+#define EVTCHNSTAT_pirq		3  /* Channel is bound to a phys IRQ line.   */
+#define EVTCHNSTAT_virq		4  /* Channel is bound to a virtual IRQ line */
+#define EVTCHNSTAT_ipi		5  /* Channel is bound to a virtual IPI line */
+	uint32_t status;
+	uint32_t vcpu;		   /* VCPU to which this channel is bound.   */
+	union {
+		struct {
+			domid_t dom;
+		} unbound; /* EVTCHNSTAT_unbound */
+		struct {
+			domid_t dom;
+			evtchn_port_t port;
+		} interdomain; /* EVTCHNSTAT_interdomain */
+		uint32_t pirq;	    /* EVTCHNSTAT_pirq	      */
+		uint32_t virq;	    /* EVTCHNSTAT_virq	      */
+	} u;
+};
+
+/*
+ * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an
+ * event is pending.
+ * NOTES:
+ *  1. IPI- and VIRQ-bound channels always notify the vcpu that initialised
+ *     the binding. This binding cannot be changed.
+ *  2. All other channels notify vcpu0 by default. This default is set when
+ *     the channel is allocated (a port that is freed and subsequently reused
+ *     has its binding reset to vcpu0).
+ */
+#define EVTCHNOP_bind_vcpu	  8
+struct evtchn_bind_vcpu {
+	/* IN parameters. */
+	evtchn_port_t port;
+	uint32_t vcpu;
+};
+
+/*
+ * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver
+ * a notification to the appropriate VCPU if an event is pending.
+ */
+#define EVTCHNOP_unmask		  9
+struct evtchn_unmask {
+	/* IN parameters. */
+	evtchn_port_t port;
+};
+
+/*
+ * EVTCHNOP_reset: Close all event channels associated with specified domain.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
+ */
+#define EVTCHNOP_reset		 10
+struct evtchn_reset {
+	/* IN parameters. */
+	domid_t dom;
+};
+typedef struct evtchn_reset evtchn_reset_t;
+
+/*
+ * EVTCHNOP_init_control: initialize the control block for the FIFO ABI.
+ */
+#define EVTCHNOP_init_control    11
+struct evtchn_init_control {
+	/* IN parameters. */
+	uint64_t control_gfn;
+	uint32_t offset;
+	uint32_t vcpu;
+	/* OUT parameters. */
+	uint8_t link_bits;
+	uint8_t _pad[7];
+};
+
+/*
+ * EVTCHNOP_expand_array: add an additional page to the event array.
+ */
+#define EVTCHNOP_expand_array    12
+struct evtchn_expand_array {
+	/* IN parameters. */
+	uint64_t array_gfn;
+};
+
+/*
+ * EVTCHNOP_set_priority: set the priority for an event channel.
+ */
+#define EVTCHNOP_set_priority    13
+struct evtchn_set_priority {
+	/* IN parameters. */
+	uint32_t port;
+	uint32_t priority;
+};
+
+struct evtchn_op {
+	uint32_t cmd; /* EVTCHNOP_* */
+	union {
+		struct evtchn_alloc_unbound    alloc_unbound;
+		struct evtchn_bind_interdomain bind_interdomain;
+		struct evtchn_bind_virq	       bind_virq;
+		struct evtchn_bind_pirq	       bind_pirq;
+		struct evtchn_bind_ipi	       bind_ipi;
+		struct evtchn_close	       close;
+		struct evtchn_send	       send;
+		struct evtchn_status	       status;
+		struct evtchn_bind_vcpu	       bind_vcpu;
+		struct evtchn_unmask	       unmask;
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(evtchn_op);
+
+/*
+ * 2-level ABI
+ */
+
+#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64)
+
+/*
+ * FIFO ABI
+ */
+
+/* Events may have priorities from 0 (highest) to 15 (lowest). */
+#define EVTCHN_FIFO_PRIORITY_MAX     0
+#define EVTCHN_FIFO_PRIORITY_DEFAULT 7
+#define EVTCHN_FIFO_PRIORITY_MIN     15
+
+#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1)
+
+typedef uint32_t event_word_t;
+
+#define EVTCHN_FIFO_PENDING 31
+#define EVTCHN_FIFO_MASKED  30
+#define EVTCHN_FIFO_LINKED  29
+#define EVTCHN_FIFO_BUSY    28
+
+#define EVTCHN_FIFO_LINK_BITS 17
+#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1)
+
+#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS)
+
+struct evtchn_fifo_control_block {
+	uint32_t     ready;
+	uint32_t     _rsvd;
+	event_word_t head[EVTCHN_FIFO_MAX_QUEUES];
+};
+
+#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */
diff --git a/kernel/include/xen/interface/features.h b/kernel/include/xen/interface/features.h
new file mode 100644
index 000000000..6ad3d110b
--- /dev/null
+++ b/kernel/include/xen/interface/features.h
@@ -0,0 +1,64 @@
+/******************************************************************************
+ * features.h
+ *
+ * Feature flags, reported by XENVER_get_features.
+ *
+ * Copyright (c) 2006, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_FEATURES_H__
+#define __XEN_PUBLIC_FEATURES_H__
+
+/*
+ * If set, the guest does not need to write-protect its pagetables, and can
+ * update them via direct writes.
+ */
+#define XENFEAT_writable_page_tables       0
+
+/*
+ * If set, the guest does not need to write-protect its segment descriptor
+ * tables, and can update them via direct writes.
+ */
+#define XENFEAT_writable_descriptor_tables 1
+
+/*
+ * If set, translation between the guest's 'pseudo-physical' address space
+ * and the host's machine address space are handled by the hypervisor. In this
+ * mode the guest does not need to perform phys-to/from-machine translations
+ * when performing page table operations.
+ */
+#define XENFEAT_auto_translated_physmap    2
+
+/* If set, the guest is running in supervisor mode (e.g., x86 ring 0). */
+#define XENFEAT_supervisor_mode_kernel     3
+
+/*
+ * If set, the guest does not need to allocate x86 PAE page directories
+ * below 4GB. This flag is usually implied by auto_translated_physmap.
+ */
+#define XENFEAT_pae_pgdir_above_4gb        4
+
+/* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */
+#define XENFEAT_mmu_pt_update_preserve_ad  5
+
+/*
+ * If set, GNTTABOP_map_grant_ref honors flags to be placed into guest kernel
+ * available pte bits.
+ */
+#define XENFEAT_gnttab_map_avail_bits      7
+
+/* x86: Does this Xen host support the HVM callback vector type? */
+#define XENFEAT_hvm_callback_vector        8
+
+/* x86: pvclock algorithm is safe to use on HVM */
+#define XENFEAT_hvm_safe_pvclock           9
+
+/* x86: pirq can be used by HVM guests */
+#define XENFEAT_hvm_pirqs           10
+
+/* operation as Dom0 is supported */
+#define XENFEAT_dom0                      11
+
+#define XENFEAT_NR_SUBMAPS 1
+
+#endif /* __XEN_PUBLIC_FEATURES_H__ */
diff --git a/kernel/include/xen/interface/grant_table.h b/kernel/include/xen/interface/grant_table.h
new file mode 100644
index 000000000..56806bc90
--- /dev/null
+++ b/kernel/include/xen/interface/grant_table.h
@@ -0,0 +1,568 @@
+/******************************************************************************
+ * grant_table.h
+ *
+ * Interface for granting foreign access to page frames, and receiving
+ * page-ownership transfers.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __XEN_PUBLIC_GRANT_TABLE_H__
+#define __XEN_PUBLIC_GRANT_TABLE_H__
+
+#include <xen/interface/xen.h>
+
+/***********************************
+ * GRANT TABLE REPRESENTATION
+ */
+
+/* Some rough guidelines on accessing and updating grant-table entries
+ * in a concurrency-safe manner. For more information, Linux contains a
+ * reference implementation for guest OSes (arch/xen/kernel/grant_table.c).
+ *
+ * NB. WMB is a no-op on current-generation x86 processors. However, a
+ *     compiler barrier will still be required.
+ *
+ * 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.
+ *
+ * Invalidating an unused GTF_permit_access entry:
+ *  1. flags = ent->flags.
+ *  2. Observe that !(flags & (GTF_reading|GTF_writing)).
+ *  3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
+ *  NB. No need for WMB as reuse of entry is control-dependent on success of
+ *      step 3, and all architectures guarantee ordering of ctrl-dep writes.
+ *
+ * Invalidating an in-use GTF_permit_access entry:
+ *  This cannot be done directly. Request assistance from the domain controller
+ *  which can set a timeout on the use of a grant entry and take necessary
+ *  action. (NB. This is not yet implemented!).
+ *
+ * Invalidating an unused GTF_accept_transfer entry:
+ *  1. flags = ent->flags.
+ *  2. Observe that !(flags & GTF_transfer_committed). [*]
+ *  3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
+ *  NB. No need for WMB as reuse of entry is control-dependent on success of
+ *      step 3, and all architectures guarantee ordering of ctrl-dep writes.
+ *  [*] If GTF_transfer_committed is set then the grant entry is 'committed'.
+ *      The guest must /not/ modify the grant entry until the address of the
+ *      transferred frame is written. It is safe for the guest to spin waiting
+ *      for this to occur (detect by observing GTF_transfer_completed in
+ *      ent->flags).
+ *
+ * Invalidating a committed GTF_accept_transfer entry:
+ *  1. Wait for (ent->flags & GTF_transfer_completed).
+ *
+ * Changing a GTF_permit_access from writable to read-only:
+ *  Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing.
+ *
+ * Changing a GTF_permit_access from read-only to writable:
+ *  Use SMP-safe bit-setting instruction.
+ */
+
+/*
+ * Reference to a grant entry in a specified domain's grant table.
+ */
+typedef uint32_t grant_ref_t;
+
+/*
+ * A grant table comprises a packed array of grant entries in one or more
+ * page frames shared between Xen and a guest.
+ * [XEN]: This field is written by Xen and read by the sharing guest.
+ * [GST]: This field is written by the guest and read by Xen.
+ */
+
+/*
+ * Version 1 of the grant table entry structure is maintained purely
+ * for backwards compatibility.  New guests should use version 2.
+ */
+struct grant_entry_v1 {
+    /* GTF_xxx: various type and flag information.  [XEN,GST] */
+    uint16_t flags;
+    /* The domain being granted foreign privileges. [GST] */
+    domid_t  domid;
+    /*
+     * GTF_permit_access: Frame that @domid is allowed to map and access. [GST]
+     * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN]
+     */
+    uint32_t frame;
+};
+
+/*
+ * Type of grant entry.
+ *  GTF_invalid: This grant entry grants no privileges.
+ *  GTF_permit_access: Allow @domid to map/access @frame.
+ *  GTF_accept_transfer: Allow @domid to transfer ownership of one page frame
+ *                       to this guest. Xen writes the page number to @frame.
+ *  GTF_transitive: Allow @domid to transitively access a subrange of
+ *                  @trans_grant in @trans_domid.  No mappings are allowed.
+ */
+#define GTF_invalid         (0U<<0)
+#define GTF_permit_access   (1U<<0)
+#define GTF_accept_transfer (2U<<0)
+#define GTF_transitive      (3U<<0)
+#define GTF_type_mask       (3U<<0)
+
+/*
+ * Subflags for GTF_permit_access.
+ *  GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST]
+ *  GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN]
+ *  GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN]
+ *  GTF_sub_page: Grant access to only a subrange of the page.  @domid
+ *                will only be allowed to copy from the grant, and not
+ *                map it. [GST]
+ */
+#define _GTF_readonly       (2)
+#define GTF_readonly        (1U<<_GTF_readonly)
+#define _GTF_reading        (3)
+#define GTF_reading         (1U<<_GTF_reading)
+#define _GTF_writing        (4)
+#define GTF_writing         (1U<<_GTF_writing)
+#define _GTF_sub_page       (8)
+#define GTF_sub_page        (1U<<_GTF_sub_page)
+
+/*
+ * Subflags for GTF_accept_transfer:
+ *  GTF_transfer_committed: Xen sets this flag to indicate that it is committed
+ *      to transferring ownership of a page frame. When a guest sees this flag
+ *      it must /not/ modify the grant entry until GTF_transfer_completed is
+ *      set by Xen.
+ *  GTF_transfer_completed: It is safe for the guest to spin-wait on this flag
+ *      after reading GTF_transfer_committed. Xen will always write the frame
+ *      address, followed by ORing this flag, in a timely manner.
+ */
+#define _GTF_transfer_committed (2)
+#define GTF_transfer_committed  (1U<<_GTF_transfer_committed)
+#define _GTF_transfer_completed (3)
+#define GTF_transfer_completed  (1U<<_GTF_transfer_completed)
+
+/*
+ * Version 2 grant table entries.  These fulfil the same role as
+ * version 1 entries, but can represent more complicated operations.
+ * Any given domain will have either a version 1 or a version 2 table,
+ * and every entry in the table will be the same version.
+ *
+ * The interface by which domains use grant references does not depend
+ * on the grant table version in use by the other domain.
+ */
+
+/*
+ * Version 1 and version 2 grant entries share a common prefix.  The
+ * fields of the prefix are documented as part of struct
+ * grant_entry_v1.
+ */
+struct grant_entry_header {
+    uint16_t flags;
+    domid_t  domid;
+};
+
+/*
+ * Version 2 of the grant entry structure, here is an union because three
+ * different types are suppotted: full_page, sub_page and transitive.
+ */
+union grant_entry_v2 {
+    struct grant_entry_header hdr;
+
+    /*
+     * This member is used for V1-style full page grants, where either:
+     *
+     * -- hdr.type is GTF_accept_transfer, or
+     * -- hdr.type is GTF_permit_access and GTF_sub_page is not set.
+     *
+     * In that case, the frame field has the same semantics as the
+     * field of the same name in the V1 entry structure.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	uint32_t pad0;
+	uint64_t frame;
+    } full_page;
+
+    /*
+     * If the grant type is GTF_grant_access and GTF_sub_page is set,
+     * @domid is allowed to access bytes [@page_off,@page_off+@length)
+     * in frame @frame.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	uint16_t page_off;
+	uint16_t length;
+	uint64_t frame;
+    } sub_page;
+
+    /*
+     * If the grant is GTF_transitive, @domid is allowed to use the
+     * grant @gref in domain @trans_domid, as if it was the local
+     * domain.  Obviously, the transitive access must be compatible
+     * with the original grant.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	domid_t trans_domid;
+	uint16_t pad0;
+	grant_ref_t gref;
+    } transitive;
+
+    uint32_t __spacer[4]; /* Pad to a power of two */
+};
+
+typedef uint16_t grant_status_t;
+
+/***********************************
+ * GRANT TABLE QUERIES AND USES
+ */
+
+/*
+ * Handle to track a mapping created via a grant reference.
+ */
+typedef uint32_t grant_handle_t;
+
+/*
+ * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access
+ * by devices and/or host CPUs. If successful, <handle> is a tracking number
+ * that must be presented later to destroy the mapping(s). On error, <handle>
+ * is a negative status code.
+ * NOTES:
+ *  1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address
+ *     via which I/O devices may access the granted frame.
+ *  2. If GNTMAP_host_map is specified then a mapping will be added at
+ *     either a host virtual address in the current address space, or at
+ *     a PTE at the specified machine address.  The type of mapping to
+ *     perform is selected through the GNTMAP_contains_pte flag, and the
+ *     address is specified in <host_addr>.
+ *  3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a
+ *     host mapping is destroyed by other means then it is *NOT* guaranteed
+ *     to be accounted to the correct grant reference!
+ */
+#define GNTTABOP_map_grant_ref        0
+struct gnttab_map_grant_ref {
+    /* IN parameters. */
+    uint64_t host_addr;
+    uint32_t flags;               /* GNTMAP_* */
+    grant_ref_t ref;
+    domid_t  dom;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+    grant_handle_t handle;
+    uint64_t dev_bus_addr;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref);
+
+/*
+ * GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings
+ * tracked by <handle>. If <host_addr> or <dev_bus_addr> is zero, that
+ * field is ignored. If non-zero, they must refer to a device/host mapping
+ * that is tracked by <handle>
+ * NOTES:
+ *  1. The call may fail in an undefined manner if either mapping is not
+ *     tracked by <handle>.
+ *  3. After executing a batch of unmaps, it is guaranteed that no stale
+ *     mappings will remain in the device or host TLBs.
+ */
+#define GNTTABOP_unmap_grant_ref      1
+struct gnttab_unmap_grant_ref {
+    /* IN parameters. */
+    uint64_t host_addr;
+    uint64_t dev_bus_addr;
+    grant_handle_t handle;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref);
+
+/*
+ * GNTTABOP_setup_table: Set up a grant table for <dom> comprising at least
+ * <nr_frames> pages. The frame addresses are written to the <frame_list>.
+ * Only <nr_frames> addresses are written, even if the table is larger.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
+ *  3. Xen may not support more than a single grant-table page per domain.
+ */
+#define GNTTABOP_setup_table          2
+struct gnttab_setup_table {
+    /* IN parameters. */
+    domid_t  dom;
+    uint32_t nr_frames;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+    GUEST_HANDLE(xen_pfn_t) frame_list;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table);
+
+/*
+ * GNTTABOP_dump_table: Dump the contents of the grant table to the
+ * xen console. Debugging use only.
+ */
+#define GNTTABOP_dump_table           3
+struct gnttab_dump_table {
+    /* IN parameters. */
+    domid_t dom;
+    /* OUT parameters. */
+    int16_t status;               /* GNTST_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table);
+
+/*
+ * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The
+ * foreign domain has previously registered its interest in the transfer via
+ * <domid, ref>.
+ *
+ * Note that, even if the transfer fails, the specified page no longer belongs
+ * to the calling domain *unless* the error is GNTST_bad_page.
+ */
+#define GNTTABOP_transfer                4
+struct gnttab_transfer {
+    /* IN parameters. */
+    xen_pfn_t mfn;
+    domid_t       domid;
+    grant_ref_t   ref;
+    /* OUT parameters. */
+    int16_t       status;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer);
+
+/*
+ * GNTTABOP_copy: Hypervisor based copy
+ * source and destinations can be eithers MFNs or, for foreign domains,
+ * grant references. the foreign domain has to grant read/write access
+ * in its grant table.
+ *
+ * The flags specify what type source and destinations are (either MFN
+ * or grant reference).
+ *
+ * Note that this can also be used to copy data between two domains
+ * via a third party if the source and destination domains had previously
+ * grant appropriate access to their pages to the third party.
+ *
+ * source_offset specifies an offset in the source frame, dest_offset
+ * the offset in the target frame and  len specifies the number of
+ * bytes to be copied.
+ */
+
+#define _GNTCOPY_source_gref      (0)
+#define GNTCOPY_source_gref       (1<<_GNTCOPY_source_gref)
+#define _GNTCOPY_dest_gref        (1)
+#define GNTCOPY_dest_gref         (1<<_GNTCOPY_dest_gref)
+
+#define GNTTABOP_copy                 5
+struct gnttab_copy {
+	/* IN parameters. */
+	struct {
+		union {
+			grant_ref_t ref;
+			xen_pfn_t   gmfn;
+		} u;
+		domid_t  domid;
+		uint16_t offset;
+	} source, dest;
+	uint16_t      len;
+	uint16_t      flags;          /* GNTCOPY_* */
+	/* OUT parameters. */
+	int16_t       status;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy);
+
+/*
+ * GNTTABOP_query_size: Query the current and maximum sizes of the shared
+ * grant table.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
+ */
+#define GNTTABOP_query_size           6
+struct gnttab_query_size {
+    /* IN parameters. */
+    domid_t  dom;
+    /* OUT parameters. */
+    uint32_t nr_frames;
+    uint32_t max_nr_frames;
+    int16_t  status;              /* GNTST_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size);
+
+/*
+ * GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings
+ * tracked by <handle> but atomically replace the page table entry with one
+ * pointing to the machine address under <new_addr>.  <new_addr> will be
+ * redirected to the null entry.
+ * NOTES:
+ *  1. The call may fail in an undefined manner if either mapping is not
+ *     tracked by <handle>.
+ *  2. After executing a batch of unmaps, it is guaranteed that no stale
+ *     mappings will remain in the device or host TLBs.
+ */
+#define GNTTABOP_unmap_and_replace    7
+struct gnttab_unmap_and_replace {
+    /* IN parameters. */
+    uint64_t host_addr;
+    uint64_t new_addr;
+    grant_handle_t handle;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace);
+
+/*
+ * GNTTABOP_set_version: Request a particular version of the grant
+ * table shared table structure.  This operation can only be performed
+ * once in any given domain.  It must be performed before any grants
+ * are activated; otherwise, the domain will be stuck with version 1.
+ * The only defined versions are 1 and 2.
+ */
+#define GNTTABOP_set_version          8
+struct gnttab_set_version {
+    /* IN parameters */
+    uint32_t version;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version);
+
+/*
+ * GNTTABOP_get_status_frames: Get the list of frames used to store grant
+ * status for <dom>. In grant format version 2, the status is separated
+ * from the other shared grant fields to allow more efficient synchronization
+ * using barriers instead of atomic cmpexch operations.
+ * <nr_frames> specify the size of vector <frame_list>.
+ * The frame addresses are returned in the <frame_list>.
+ * Only <nr_frames> addresses are returned, even if the table is larger.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
+ */
+#define GNTTABOP_get_status_frames     9
+struct gnttab_get_status_frames {
+    /* IN parameters. */
+    uint32_t nr_frames;
+    domid_t  dom;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+    GUEST_HANDLE(uint64_t) frame_list;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames);
+
+/*
+ * GNTTABOP_get_version: Get the grant table version which is in
+ * effect for domain <dom>.
+ */
+#define GNTTABOP_get_version          10
+struct gnttab_get_version {
+    /* IN parameters */
+    domid_t dom;
+    uint16_t pad;
+    /* OUT parameters */
+    uint32_t version;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version);
+
+/*
+ * Issue one or more cache maintenance operations on a portion of a
+ * page granted to the calling domain by a foreign domain.
+ */
+#define GNTTABOP_cache_flush          12
+struct gnttab_cache_flush {
+    union {
+        uint64_t dev_bus_addr;
+        grant_ref_t ref;
+    } a;
+    uint16_t offset;   /* offset from start of grant */
+    uint16_t length;   /* size within the grant */
+#define GNTTAB_CACHE_CLEAN          (1<<0)
+#define GNTTAB_CACHE_INVAL          (1<<1)
+#define GNTTAB_CACHE_SOURCE_GREF    (1<<31)
+    uint32_t op;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush);
+
+/*
+ * Bitfield values for update_pin_status.flags.
+ */
+ /* Map the grant entry for access by I/O devices. */
+#define _GNTMAP_device_map      (0)
+#define GNTMAP_device_map       (1<<_GNTMAP_device_map)
+ /* Map the grant entry for access by host CPUs. */
+#define _GNTMAP_host_map        (1)
+#define GNTMAP_host_map         (1<<_GNTMAP_host_map)
+ /* Accesses to the granted frame will be restricted to read-only access. */
+#define _GNTMAP_readonly        (2)
+#define GNTMAP_readonly         (1<<_GNTMAP_readonly)
+ /*
+  * GNTMAP_host_map subflag:
+  *  0 => The host mapping is usable only by the guest OS.
+  *  1 => The host mapping is usable by guest OS + current application.
+  */
+#define _GNTMAP_application_map (3)
+#define GNTMAP_application_map  (1<<_GNTMAP_application_map)
+
+ /*
+  * GNTMAP_contains_pte subflag:
+  *  0 => This map request contains a host virtual address.
+  *  1 => This map request contains the machine addess of the PTE to update.
+  */
+#define _GNTMAP_contains_pte    (4)
+#define GNTMAP_contains_pte     (1<<_GNTMAP_contains_pte)
+
+/*
+ * Bits to be placed in guest kernel available PTE bits (architecture
+ * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set).
+ */
+#define _GNTMAP_guest_avail0    (16)
+#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0)
+
+/*
+ * Values for error status returns. All errors are -ve.
+ */
+#define GNTST_okay             (0)  /* Normal return.                        */
+#define GNTST_general_error    (-1) /* General undefined error.              */
+#define GNTST_bad_domain       (-2) /* Unrecognsed domain id.                */
+#define GNTST_bad_gntref       (-3) /* Unrecognised or inappropriate gntref. */
+#define GNTST_bad_handle       (-4) /* Unrecognised or inappropriate handle. */
+#define GNTST_bad_virt_addr    (-5) /* Inappropriate virtual address to map. */
+#define GNTST_bad_dev_addr     (-6) /* Inappropriate device address to unmap.*/
+#define GNTST_no_device_space  (-7) /* Out of space in I/O MMU.              */
+#define GNTST_permission_denied (-8) /* Not enough privilege for operation.  */
+#define GNTST_bad_page         (-9) /* Specified page was invalid for op.    */
+#define GNTST_bad_copy_arg    (-10) /* copy arguments cross page boundary.   */
+#define GNTST_address_too_big (-11) /* transfer page address too large.      */
+#define GNTST_eagain          (-12) /* Operation not done; try again.        */
+
+#define GNTTABOP_error_msgs {                   \
+    "okay",                                     \
+    "undefined error",                          \
+    "unrecognised domain id",                   \
+    "invalid grant reference",                  \
+    "invalid mapping handle",                   \
+    "invalid virtual address",                  \
+    "invalid device address",                   \
+    "no spare translation slot in the I/O MMU", \
+    "permission denied",                        \
+    "bad page",                                 \
+    "copy arguments cross page boundary",       \
+    "page address size too large",              \
+    "operation not done; try again"             \
+}
+
+#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */
diff --git a/kernel/include/xen/interface/hvm/hvm_op.h b/kernel/include/xen/interface/hvm/hvm_op.h
new file mode 100644
index 000000000..956a04682
--- /dev/null
+++ b/kernel/include/xen/interface/hvm/hvm_op.h
@@ -0,0 +1,65 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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 __XEN_PUBLIC_HVM_HVM_OP_H__
+#define __XEN_PUBLIC_HVM_HVM_OP_H__
+
+/* Get/set subcommands: the second argument of the hypercall is a
+ * pointer to a xen_hvm_param struct. */
+#define HVMOP_set_param           0
+#define HVMOP_get_param           1
+struct xen_hvm_param {
+    domid_t  domid;    /* IN */
+    uint32_t index;    /* IN */
+    uint64_t value;    /* IN/OUT */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_param);
+
+/* Hint from PV drivers for pagetable destruction. */
+#define HVMOP_pagetable_dying       9
+struct xen_hvm_pagetable_dying {
+    /* Domain with a pagetable about to be destroyed. */
+    domid_t  domid;
+    /* guest physical address of the toplevel pagetable dying */
+    aligned_u64 gpa;
+};
+typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t;
+DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_pagetable_dying_t);
+ 
+enum hvmmem_type_t {
+    HVMMEM_ram_rw,             /* Normal read/write guest RAM */
+    HVMMEM_ram_ro,             /* Read-only; writes are discarded */
+    HVMMEM_mmio_dm,            /* Reads and write go to the device model */
+};
+
+#define HVMOP_get_mem_type    15
+/* Return hvmmem_type_t for the specified pfn. */
+struct xen_hvm_get_mem_type {
+    /* Domain to be queried. */
+    domid_t domid;
+    /* OUT variable. */
+    uint16_t mem_type;
+    uint16_t pad[2]; /* align next field on 8-byte boundary */
+    /* IN variable. */
+    uint64_t pfn;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_get_mem_type);
+
+#endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */
diff --git a/kernel/include/xen/interface/hvm/params.h b/kernel/include/xen/interface/hvm/params.h
new file mode 100644
index 000000000..a6c79911e
--- /dev/null
+++ b/kernel/include/xen/interface/hvm/params.h
@@ -0,0 +1,99 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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 __XEN_PUBLIC_HVM_PARAMS_H__
+#define __XEN_PUBLIC_HVM_PARAMS_H__
+
+#include <xen/interface/hvm/hvm_op.h>
+
+/*
+ * Parameter space for HVMOP_{set,get}_param.
+ */
+
+/*
+ * How should CPU0 event-channel notifications be delivered?
+ * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt).
+ * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows:
+ *                  Domain = val[47:32], Bus  = val[31:16],
+ *                  DevFn  = val[15: 8], IntX = val[ 1: 0]
+ * val[63:56] == 2: val[7:0] is a vector number.
+ * If val == 0 then CPU0 event-channel notifications are not delivered.
+ */
+#define HVM_PARAM_CALLBACK_IRQ 0
+
+#define HVM_PARAM_STORE_PFN    1
+#define HVM_PARAM_STORE_EVTCHN 2
+
+#define HVM_PARAM_PAE_ENABLED  4
+
+#define HVM_PARAM_IOREQ_PFN    5
+
+#define HVM_PARAM_BUFIOREQ_PFN 6
+
+/*
+ * Set mode for virtual timers (currently x86 only):
+ *  delay_for_missed_ticks (default):
+ *   Do not advance a vcpu's time beyond the correct delivery time for
+ *   interrupts that have been missed due to preemption. Deliver missed
+ *   interrupts when the vcpu is rescheduled and advance the vcpu's virtual
+ *   time stepwise for each one.
+ *  no_delay_for_missed_ticks:
+ *   As above, missed interrupts are delivered, but guest time always tracks
+ *   wallclock (i.e., real) time while doing so.
+ *  no_missed_ticks_pending:
+ *   No missed interrupts are held pending. Instead, to ensure ticks are
+ *   delivered at some non-zero rate, if we detect missed ticks then the
+ *   internal tick alarm is not disabled if the VCPU is preempted during the
+ *   next tick period.
+ *  one_missed_tick_pending:
+ *   Missed interrupts are collapsed together and delivered as one 'late tick'.
+ *   Guest time always tracks wallclock (i.e., real) time.
+ */
+#define HVM_PARAM_TIMER_MODE   10
+#define HVMPTM_delay_for_missed_ticks    0
+#define HVMPTM_no_delay_for_missed_ticks 1
+#define HVMPTM_no_missed_ticks_pending   2
+#define HVMPTM_one_missed_tick_pending   3
+
+/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */
+#define HVM_PARAM_HPET_ENABLED 11
+
+/* Identity-map page directory used by Intel EPT when CR0.PG=0. */
+#define HVM_PARAM_IDENT_PT     12
+
+/* Device Model domain, defaults to 0. */
+#define HVM_PARAM_DM_DOMAIN    13
+
+/* ACPI S state: currently support S0 and S3 on x86. */
+#define HVM_PARAM_ACPI_S_STATE 14
+
+/* TSS used on Intel when CR0.PE=0. */
+#define HVM_PARAM_VM86_TSS     15
+
+/* Boolean: Enable aligning all periodic vpts to reduce interrupts */
+#define HVM_PARAM_VPT_ALIGN    16
+
+/* Console debug shared memory ring and event channel */
+#define HVM_PARAM_CONSOLE_PFN    17
+#define HVM_PARAM_CONSOLE_EVTCHN 18
+
+#define HVM_NR_PARAMS          19
+
+#endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */
diff --git a/kernel/include/xen/interface/io/blkif.h b/kernel/include/xen/interface/io/blkif.h
new file mode 100644
index 000000000..c33e1c489
--- /dev/null
+++ b/kernel/include/xen/interface/io/blkif.h
@@ -0,0 +1,253 @@
+/******************************************************************************
+ * blkif.h
+ *
+ * Unified block-device I/O interface for Xen guest OSes.
+ *
+ * Copyright (c) 2003-2004, Keir Fraser
+ */
+
+#ifndef __XEN_PUBLIC_IO_BLKIF_H__
+#define __XEN_PUBLIC_IO_BLKIF_H__
+
+#include <xen/interface/io/ring.h>
+#include <xen/interface/grant_table.h>
+
+/*
+ * Front->back notifications: When enqueuing a new request, sending a
+ * notification can be made conditional on req_event (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Backends must set
+ * req_event appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()).
+ *
+ * Back->front notifications: When enqueuing a new response, sending a
+ * notification can be made conditional on rsp_event (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Frontends must set
+ * rsp_event appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()).
+ */
+
+typedef uint16_t blkif_vdev_t;
+typedef uint64_t blkif_sector_t;
+
+/*
+ * REQUEST CODES.
+ */
+#define BLKIF_OP_READ              0
+#define BLKIF_OP_WRITE             1
+/*
+ * Recognised only if "feature-barrier" is present in backend xenbus info.
+ * The "feature_barrier" node contains a boolean indicating whether barrier
+ * requests are likely to succeed or fail. Either way, a barrier request
+ * may fail at any time with BLKIF_RSP_EOPNOTSUPP if it is unsupported by
+ * the underlying block-device hardware. The boolean simply indicates whether
+ * or not it is worthwhile for the frontend to attempt barrier requests.
+ * If a backend does not recognise BLKIF_OP_WRITE_BARRIER, it should *not*
+ * create the "feature-barrier" node!
+ */
+#define BLKIF_OP_WRITE_BARRIER     2
+
+/*
+ * Recognised if "feature-flush-cache" is present in backend xenbus
+ * info.  A flush will ask the underlying storage hardware to flush its
+ * non-volatile caches as appropriate.  The "feature-flush-cache" node
+ * contains a boolean indicating whether flush requests are likely to
+ * succeed or fail. Either way, a flush request may fail at any time
+ * with BLKIF_RSP_EOPNOTSUPP if it is unsupported by the underlying
+ * block-device hardware. The boolean simply indicates whether or not it
+ * is worthwhile for the frontend to attempt flushes.  If a backend does
+ * not recognise BLKIF_OP_WRITE_FLUSH_CACHE, it should *not* create the
+ * "feature-flush-cache" node!
+ */
+#define BLKIF_OP_FLUSH_DISKCACHE   3
+
+/*
+ * Recognised only if "feature-discard" is present in backend xenbus info.
+ * The "feature-discard" node contains a boolean indicating whether trim
+ * (ATA) or unmap (SCSI) - conviently called discard requests are likely
+ * to succeed or fail. Either way, a discard request
+ * may fail at any time with BLKIF_RSP_EOPNOTSUPP if it is unsupported by
+ * the underlying block-device hardware. The boolean simply indicates whether
+ * or not it is worthwhile for the frontend to attempt discard requests.
+ * If a backend does not recognise BLKIF_OP_DISCARD, it should *not*
+ * create the "feature-discard" node!
+ *
+ * Discard operation is a request for the underlying block device to mark
+ * extents to be erased. However, discard does not guarantee that the blocks
+ * will be erased from the device - it is just a hint to the device
+ * controller that these blocks are no longer in use. What the device
+ * controller does with that information is left to the controller.
+ * Discard operations are passed with sector_number as the
+ * sector index to begin discard operations at and nr_sectors as the number of
+ * sectors to be discarded. The specified sectors should be discarded if the
+ * underlying block device supports trim (ATA) or unmap (SCSI) operations,
+ * or a BLKIF_RSP_EOPNOTSUPP  should be returned.
+ * More information about trim/unmap operations at:
+ * http://t13.org/Documents/UploadedDocuments/docs2008/
+ *     e07154r6-Data_Set_Management_Proposal_for_ATA-ACS2.doc
+ * http://www.seagate.com/staticfiles/support/disc/manuals/
+ *     Interface%20manuals/100293068c.pdf
+ * The backend can optionally provide three extra XenBus attributes to
+ * further optimize the discard functionality:
+ * 'discard-alignment' - Devices that support discard functionality may
+ * internally allocate space in units that are bigger than the exported
+ * logical block size. The discard-alignment parameter indicates how many bytes
+ * the beginning of the partition is offset from the internal allocation unit's
+ * natural alignment.
+ * 'discard-granularity'  - Devices that support discard functionality may
+ * internally allocate space using units that are bigger than the logical block
+ * size. The discard-granularity parameter indicates the size of the internal
+ * allocation unit in bytes if reported by the device. Otherwise the
+ * discard-granularity will be set to match the device's physical block size.
+ * 'discard-secure' - All copies of the discarded sectors (potentially created
+ * by garbage collection) must also be erased.  To use this feature, the flag
+ * BLKIF_DISCARD_SECURE must be set in the blkif_request_trim.
+ */
+#define BLKIF_OP_DISCARD           5
+
+/*
+ * Recognized if "feature-max-indirect-segments" in present in the backend
+ * xenbus info. The "feature-max-indirect-segments" node contains the maximum
+ * number of segments allowed by the backend per request. If the node is
+ * present, the frontend might use blkif_request_indirect structs in order to
+ * issue requests with more than BLKIF_MAX_SEGMENTS_PER_REQUEST (11). The
+ * maximum number of indirect segments is fixed by the backend, but the
+ * frontend can issue requests with any number of indirect segments as long as
+ * it's less than the number provided by the backend. The indirect_grefs field
+ * in blkif_request_indirect should be filled by the frontend with the
+ * grant references of the pages that are holding the indirect segments.
+ * These pages are filled with an array of blkif_request_segment that hold the
+ * information about the segments. The number of indirect pages to use is
+ * determined by the number of segments an indirect request contains. Every
+ * indirect page can contain a maximum of
+ * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to
+ * calculate the number of indirect pages to use we have to do
+ * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))).
+ *
+ * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not*
+ * create the "feature-max-indirect-segments" node!
+ */
+#define BLKIF_OP_INDIRECT          6
+
+/*
+ * Maximum scatter/gather segments per request.
+ * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE.
+ * NB. This could be 12 if the ring indexes weren't stored in the same page.
+ */
+#define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
+
+#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8
+
+struct blkif_request_segment {
+		grant_ref_t gref;        /* reference to I/O buffer frame        */
+		/* @first_sect: first sector in frame to transfer (inclusive).   */
+		/* @last_sect: last sector in frame to transfer (inclusive).     */
+		uint8_t     first_sect, last_sect;
+};
+
+struct blkif_request_rw {
+	uint8_t        nr_segments;  /* number of segments                   */
+	blkif_vdev_t   handle;       /* only for read/write requests         */
+#ifndef CONFIG_X86_32
+	uint32_t       _pad1;	     /* offsetof(blkif_request,u.rw.id) == 8 */
+#endif
+	uint64_t       id;           /* private guest value, echoed in resp  */
+	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
+	struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+} __attribute__((__packed__));
+
+struct blkif_request_discard {
+	uint8_t        flag;         /* BLKIF_DISCARD_SECURE or zero.        */
+#define BLKIF_DISCARD_SECURE (1<<0)  /* ignored if discard-secure=0          */
+	blkif_vdev_t   _pad1;        /* only for read/write requests         */
+#ifndef CONFIG_X86_32
+	uint32_t       _pad2;        /* offsetof(blkif_req..,u.discard.id)==8*/
+#endif
+	uint64_t       id;           /* private guest value, echoed in resp  */
+	blkif_sector_t sector_number;
+	uint64_t       nr_sectors;
+	uint8_t        _pad3;
+} __attribute__((__packed__));
+
+struct blkif_request_other {
+	uint8_t      _pad1;
+	blkif_vdev_t _pad2;        /* only for read/write requests         */
+#ifndef CONFIG_X86_32
+	uint32_t     _pad3;        /* offsetof(blkif_req..,u.other.id)==8*/
+#endif
+	uint64_t     id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
+struct blkif_request_indirect {
+	uint8_t        indirect_op;
+	uint16_t       nr_segments;
+#ifndef CONFIG_X86_32
+	uint32_t       _pad1;        /* offsetof(blkif_...,u.indirect.id) == 8 */
+#endif
+	uint64_t       id;
+	blkif_sector_t sector_number;
+	blkif_vdev_t   handle;
+	uint16_t       _pad2;
+	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
+#ifndef CONFIG_X86_32
+	uint32_t      _pad3;         /* make it 64 byte aligned */
+#else
+	uint64_t      _pad3;         /* make it 64 byte aligned */
+#endif
+} __attribute__((__packed__));
+
+struct blkif_request {
+	uint8_t        operation;    /* BLKIF_OP_???                         */
+	union {
+		struct blkif_request_rw rw;
+		struct blkif_request_discard discard;
+		struct blkif_request_other other;
+		struct blkif_request_indirect indirect;
+	} u;
+} __attribute__((__packed__));
+
+struct blkif_response {
+	uint64_t        id;              /* copied from request */
+	uint8_t         operation;       /* copied from request */
+	int16_t         status;          /* BLKIF_RSP_???       */
+};
+
+/*
+ * STATUS RETURN CODES.
+ */
+ /* Operation not supported (only happens on barrier writes). */
+#define BLKIF_RSP_EOPNOTSUPP  -2
+ /* Operation failed for some unspecified reason (-EIO). */
+#define BLKIF_RSP_ERROR       -1
+ /* Operation completed successfully. */
+#define BLKIF_RSP_OKAY         0
+
+/*
+ * Generate blkif ring structures and types.
+ */
+
+DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
+
+#define VDISK_CDROM        0x1
+#define VDISK_REMOVABLE    0x2
+#define VDISK_READONLY     0x4
+
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR	3
+#define XEN_IDE1_MAJOR	22
+#define XEN_SCSI_DISK0_MAJOR	8
+#define XEN_SCSI_DISK1_MAJOR	65
+#define XEN_SCSI_DISK2_MAJOR	66
+#define XEN_SCSI_DISK3_MAJOR	67
+#define XEN_SCSI_DISK4_MAJOR	68
+#define XEN_SCSI_DISK5_MAJOR	69
+#define XEN_SCSI_DISK6_MAJOR	70
+#define XEN_SCSI_DISK7_MAJOR	71
+#define XEN_SCSI_DISK8_MAJOR	128
+#define XEN_SCSI_DISK9_MAJOR	129
+#define XEN_SCSI_DISK10_MAJOR	130
+#define XEN_SCSI_DISK11_MAJOR	131
+#define XEN_SCSI_DISK12_MAJOR	132
+#define XEN_SCSI_DISK13_MAJOR	133
+#define XEN_SCSI_DISK14_MAJOR	134
+#define XEN_SCSI_DISK15_MAJOR	135
+
+#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
diff --git a/kernel/include/xen/interface/io/console.h b/kernel/include/xen/interface/io/console.h
new file mode 100644
index 000000000..e563de70f
--- /dev/null
+++ b/kernel/include/xen/interface/io/console.h
@@ -0,0 +1,23 @@
+/******************************************************************************
+ * console.h
+ *
+ * Console I/O interface for Xen guest OSes.
+ *
+ * Copyright (c) 2005, Keir Fraser
+ */
+
+#ifndef __XEN_PUBLIC_IO_CONSOLE_H__
+#define __XEN_PUBLIC_IO_CONSOLE_H__
+
+typedef uint32_t XENCONS_RING_IDX;
+
+#define MASK_XENCONS_IDX(idx, ring) ((idx) & (sizeof(ring)-1))
+
+struct xencons_interface {
+    char in[1024];
+    char out[2048];
+    XENCONS_RING_IDX in_cons, in_prod;
+    XENCONS_RING_IDX out_cons, out_prod;
+};
+
+#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */
diff --git a/kernel/include/xen/interface/io/fbif.h b/kernel/include/xen/interface/io/fbif.h
new file mode 100644
index 000000000..974a51ed9
--- /dev/null
+++ b/kernel/include/xen/interface/io/fbif.h
@@ -0,0 +1,143 @@
+/*
+ * fbif.h -- Xen virtual frame buffer device
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (C) 2005 Anthony Liguori <aliguori@us.ibm.com>
+ * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com>
+ */
+
+#ifndef __XEN_PUBLIC_IO_FBIF_H__
+#define __XEN_PUBLIC_IO_FBIF_H__
+
+/* Out events (frontend -> backend) */
+
+/*
+ * Out events may be sent only when requested by backend, and receipt
+ * of an unknown out event is an error.
+ */
+
+/* Event type 1 currently not used */
+/*
+ * Framebuffer update notification event
+ * Capable frontend sets feature-update in xenstore.
+ * Backend requests it by setting request-update in xenstore.
+ */
+#define XENFB_TYPE_UPDATE 2
+
+struct xenfb_update {
+	uint8_t type;		/* XENFB_TYPE_UPDATE */
+	int32_t x;		/* source x */
+	int32_t y;		/* source y */
+	int32_t width;		/* rect width */
+	int32_t height;		/* rect height */
+};
+
+/*
+ * Framebuffer resize notification event
+ * Capable backend sets feature-resize in xenstore.
+ */
+#define XENFB_TYPE_RESIZE 3
+
+struct xenfb_resize {
+	uint8_t type;		/* XENFB_TYPE_RESIZE */
+	int32_t width;		/* width in pixels */
+	int32_t height;		/* height in pixels */
+	int32_t stride;		/* stride in bytes */
+	int32_t depth;		/* depth in bits */
+	int32_t offset;		/* start offset within framebuffer */
+};
+
+#define XENFB_OUT_EVENT_SIZE 40
+
+union xenfb_out_event {
+	uint8_t type;
+	struct xenfb_update update;
+	struct xenfb_resize resize;
+	char pad[XENFB_OUT_EVENT_SIZE];
+};
+
+/* In events (backend -> frontend) */
+
+/*
+ * Frontends should ignore unknown in events.
+ * No in events currently defined.
+ */
+
+#define XENFB_IN_EVENT_SIZE 40
+
+union xenfb_in_event {
+	uint8_t type;
+	char pad[XENFB_IN_EVENT_SIZE];
+};
+
+/* shared page */
+
+#define XENFB_IN_RING_SIZE 1024
+#define XENFB_IN_RING_LEN (XENFB_IN_RING_SIZE / XENFB_IN_EVENT_SIZE)
+#define XENFB_IN_RING_OFFS 1024
+#define XENFB_IN_RING(page) \
+	((union xenfb_in_event *)((char *)(page) + XENFB_IN_RING_OFFS))
+#define XENFB_IN_RING_REF(page, idx) \
+	(XENFB_IN_RING((page))[(idx) % XENFB_IN_RING_LEN])
+
+#define XENFB_OUT_RING_SIZE 2048
+#define XENFB_OUT_RING_LEN (XENFB_OUT_RING_SIZE / XENFB_OUT_EVENT_SIZE)
+#define XENFB_OUT_RING_OFFS (XENFB_IN_RING_OFFS + XENFB_IN_RING_SIZE)
+#define XENFB_OUT_RING(page) \
+	((union xenfb_out_event *)((char *)(page) + XENFB_OUT_RING_OFFS))
+#define XENFB_OUT_RING_REF(page, idx) \
+	(XENFB_OUT_RING((page))[(idx) % XENFB_OUT_RING_LEN])
+
+struct xenfb_page {
+	uint32_t in_cons, in_prod;
+	uint32_t out_cons, out_prod;
+
+	int32_t width;          /* width of the framebuffer (in pixels) */
+	int32_t height;         /* height of the framebuffer (in pixels) */
+	uint32_t line_length;   /* length of a row of pixels (in bytes) */
+	uint32_t mem_length;    /* length of the framebuffer (in bytes) */
+	uint8_t depth;          /* depth of a pixel (in bits) */
+
+	/*
+	 * Framebuffer page directory
+	 *
+	 * Each directory page holds PAGE_SIZE / sizeof(*pd)
+	 * framebuffer pages, and can thus map up to PAGE_SIZE *
+	 * PAGE_SIZE / sizeof(*pd) bytes.  With PAGE_SIZE == 4096 and
+	 * sizeof(unsigned long) == 4/8, that's 4 Megs 32 bit and 2
+	 * Megs 64 bit.  256 directories give enough room for a 512
+	 * Meg framebuffer with a max resolution of 12,800x10,240.
+	 * Should be enough for a while with room leftover for
+	 * expansion.
+	 */
+	unsigned long pd[256];
+};
+
+/*
+ * Wart: xenkbd needs to know default resolution.  Put it here until a
+ * better solution is found, but don't leak it to the backend.
+ */
+#ifdef __KERNEL__
+#define XENFB_WIDTH 800
+#define XENFB_HEIGHT 600
+#define XENFB_DEPTH 32
+#endif
+
+#endif
diff --git a/kernel/include/xen/interface/io/kbdif.h b/kernel/include/xen/interface/io/kbdif.h
new file mode 100644
index 000000000..8066c7849
--- /dev/null
+++ b/kernel/include/xen/interface/io/kbdif.h
@@ -0,0 +1,116 @@
+/*
+ * kbdif.h -- Xen virtual keyboard/mouse
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (C) 2005 Anthony Liguori <aliguori@us.ibm.com>
+ * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com>
+ */
+
+#ifndef __XEN_PUBLIC_IO_KBDIF_H__
+#define __XEN_PUBLIC_IO_KBDIF_H__
+
+/* In events (backend -> frontend) */
+
+/*
+ * Frontends should ignore unknown in events.
+ */
+
+/* Pointer movement event */
+#define XENKBD_TYPE_MOTION  1
+/* Event type 2 currently not used */
+/* Key event (includes pointer buttons) */
+#define XENKBD_TYPE_KEY     3
+/*
+ * Pointer position event
+ * Capable backend sets feature-abs-pointer in xenstore.
+ * Frontend requests ot instead of XENKBD_TYPE_MOTION by setting
+ * request-abs-update in xenstore.
+ */
+#define XENKBD_TYPE_POS     4
+
+struct xenkbd_motion {
+	uint8_t type;		/* XENKBD_TYPE_MOTION */
+	int32_t rel_x;		/* relative X motion */
+	int32_t rel_y;		/* relative Y motion */
+	int32_t rel_z;		/* relative Z motion (wheel) */
+};
+
+struct xenkbd_key {
+	uint8_t type;		/* XENKBD_TYPE_KEY */
+	uint8_t pressed;	/* 1 if pressed; 0 otherwise */
+	uint32_t keycode;	/* KEY_* from linux/input.h */
+};
+
+struct xenkbd_position {
+	uint8_t type;		/* XENKBD_TYPE_POS */
+	int32_t abs_x;		/* absolute X position (in FB pixels) */
+	int32_t abs_y;		/* absolute Y position (in FB pixels) */
+	int32_t rel_z;		/* relative Z motion (wheel) */
+};
+
+#define XENKBD_IN_EVENT_SIZE 40
+
+union xenkbd_in_event {
+	uint8_t type;
+	struct xenkbd_motion motion;
+	struct xenkbd_key key;
+	struct xenkbd_position pos;
+	char pad[XENKBD_IN_EVENT_SIZE];
+};
+
+/* Out events (frontend -> backend) */
+
+/*
+ * Out events may be sent only when requested by backend, and receipt
+ * of an unknown out event is an error.
+ * No out events currently defined.
+ */
+
+#define XENKBD_OUT_EVENT_SIZE 40
+
+union xenkbd_out_event {
+	uint8_t type;
+	char pad[XENKBD_OUT_EVENT_SIZE];
+};
+
+/* shared page */
+
+#define XENKBD_IN_RING_SIZE 2048
+#define XENKBD_IN_RING_LEN (XENKBD_IN_RING_SIZE / XENKBD_IN_EVENT_SIZE)
+#define XENKBD_IN_RING_OFFS 1024
+#define XENKBD_IN_RING(page) \
+	((union xenkbd_in_event *)((char *)(page) + XENKBD_IN_RING_OFFS))
+#define XENKBD_IN_RING_REF(page, idx) \
+	(XENKBD_IN_RING((page))[(idx) % XENKBD_IN_RING_LEN])
+
+#define XENKBD_OUT_RING_SIZE 1024
+#define XENKBD_OUT_RING_LEN (XENKBD_OUT_RING_SIZE / XENKBD_OUT_EVENT_SIZE)
+#define XENKBD_OUT_RING_OFFS (XENKBD_IN_RING_OFFS + XENKBD_IN_RING_SIZE)
+#define XENKBD_OUT_RING(page) \
+	((union xenkbd_out_event *)((char *)(page) + XENKBD_OUT_RING_OFFS))
+#define XENKBD_OUT_RING_REF(page, idx) \
+	(XENKBD_OUT_RING((page))[(idx) % XENKBD_OUT_RING_LEN])
+
+struct xenkbd_page {
+	uint32_t in_cons, in_prod;
+	uint32_t out_cons, out_prod;
+};
+
+#endif
diff --git a/kernel/include/xen/interface/io/netif.h b/kernel/include/xen/interface/io/netif.h
new file mode 100644
index 000000000..70054cc07
--- /dev/null
+++ b/kernel/include/xen/interface/io/netif.h
@@ -0,0 +1,262 @@
+/******************************************************************************
+ * netif.h
+ *
+ * Unified network-device I/O interface for Xen guest OSes.
+ *
+ * Copyright (c) 2003-2004, Keir Fraser
+ */
+
+#ifndef __XEN_PUBLIC_IO_NETIF_H__
+#define __XEN_PUBLIC_IO_NETIF_H__
+
+#include <xen/interface/io/ring.h>
+#include <xen/interface/grant_table.h>
+
+/*
+ * Older implementation of Xen network frontend / backend has an
+ * implicit dependency on the MAX_SKB_FRAGS as the maximum number of
+ * ring slots a skb can use. Netfront / netback may not work as
+ * expected when frontend and backend have different MAX_SKB_FRAGS.
+ *
+ * A better approach is to add mechanism for netfront / netback to
+ * negotiate this value. However we cannot fix all possible
+ * frontends, so we need to define a value which states the minimum
+ * slots backend must support.
+ *
+ * The minimum value derives from older Linux kernel's MAX_SKB_FRAGS
+ * (18), which is proved to work with most frontends. Any new backend
+ * which doesn't negotiate with frontend should expect frontend to
+ * send a valid packet using slots up to this value.
+ */
+#define XEN_NETIF_NR_SLOTS_MIN 18
+
+/*
+ * Notifications after enqueuing any type of message should be conditional on
+ * the appropriate req_event or rsp_event field in the shared ring.
+ * If the client sends notification for rx requests then it should specify
+ * feature 'feature-rx-notify' via xenbus. Otherwise the backend will assume
+ * that it cannot safely queue packets (as it may not be kicked to send them).
+ */
+
+ /*
+ * "feature-split-event-channels" is introduced to separate guest TX
+ * and RX notificaion. Backend either doesn't support this feature or
+ * advertise it via xenstore as 0 (disabled) or 1 (enabled).
+ *
+ * To make use of this feature, frontend should allocate two event
+ * channels for TX and RX, advertise them to backend as
+ * "event-channel-tx" and "event-channel-rx" respectively. If frontend
+ * doesn't want to use this feature, it just writes "event-channel"
+ * node as before.
+ */
+
+/*
+ * Multiple transmit and receive queues:
+ * If supported, the backend will write the key "multi-queue-max-queues" to
+ * the directory for that vif, and set its value to the maximum supported
+ * number of queues.
+ * Frontends that are aware of this feature and wish to use it can write the
+ * key "multi-queue-num-queues", set to the number they wish to use, which
+ * must be greater than zero, and no more than the value reported by the backend
+ * in "multi-queue-max-queues".
+ *
+ * Queues replicate the shared rings and event channels.
+ * "feature-split-event-channels" may optionally be used when using
+ * multiple queues, but is not mandatory.
+ *
+ * Each queue consists of one shared ring pair, i.e. there must be the same
+ * number of tx and rx rings.
+ *
+ * For frontends requesting just one queue, the usual event-channel and
+ * ring-ref keys are written as before, simplifying the backend processing
+ * to avoid distinguishing between a frontend that doesn't understand the
+ * multi-queue feature, and one that does, but requested only one queue.
+ *
+ * Frontends requesting two or more queues must not write the toplevel
+ * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys,
+ * instead writing those keys under sub-keys having the name "queue-N" where
+ * N is the integer ID of the queue for which those keys belong. Queues
+ * are indexed from zero. For example, a frontend with two queues and split
+ * event channels must write the following set of queue-related keys:
+ *
+ * /local/domain/1/device/vif/0/multi-queue-num-queues = "2"
+ * /local/domain/1/device/vif/0/queue-0 = ""
+ * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>"
+ * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>"
+ * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>"
+ * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>"
+ * /local/domain/1/device/vif/0/queue-1 = ""
+ * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>"
+ * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1"
+ * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>"
+ * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>"
+ *
+ * If there is any inconsistency in the XenStore data, the backend may
+ * choose not to connect any queues, instead treating the request as an
+ * error. This includes scenarios where more (or fewer) queues were
+ * requested than the frontend provided details for.
+ *
+ * Mapping of packets to queues is considered to be a function of the
+ * transmitting system (backend or frontend) and is not negotiated
+ * between the two. Guests are free to transmit packets on any queue
+ * they choose, provided it has been set up correctly. Guests must be
+ * prepared to receive packets on any queue they have requested be set up.
+ */
+
+/*
+ * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum
+ * offload off or on. If it is missing then the feature is assumed to be on.
+ * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum
+ * offload on or off. If it is missing then the feature is assumed to be off.
+ */
+
+/*
+ * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to
+ * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither
+ * frontends nor backends are assumed to be capable unless the flags are
+ * present.
+ */
+
+/*
+ * This is the 'wire' format for packets:
+ *  Request 1: xen_netif_tx_request  -- XEN_NETTXF_* (any flags)
+ * [Request 2: xen_netif_extra_info]    (only if request 1 has XEN_NETTXF_extra_info)
+ * [Request 3: xen_netif_extra_info]    (only if request 2 has XEN_NETIF_EXTRA_MORE)
+ *  Request 4: xen_netif_tx_request  -- XEN_NETTXF_more_data
+ *  Request 5: xen_netif_tx_request  -- XEN_NETTXF_more_data
+ *  ...
+ *  Request N: xen_netif_tx_request  -- 0
+ */
+
+/* Protocol checksum field is blank in the packet (hardware offload)? */
+#define _XEN_NETTXF_csum_blank		(0)
+#define  XEN_NETTXF_csum_blank		(1U<<_XEN_NETTXF_csum_blank)
+
+/* Packet data has been validated against protocol checksum. */
+#define _XEN_NETTXF_data_validated	(1)
+#define  XEN_NETTXF_data_validated	(1U<<_XEN_NETTXF_data_validated)
+
+/* Packet continues in the next request descriptor. */
+#define _XEN_NETTXF_more_data		(2)
+#define  XEN_NETTXF_more_data		(1U<<_XEN_NETTXF_more_data)
+
+/* Packet to be followed by extra descriptor(s). */
+#define _XEN_NETTXF_extra_info		(3)
+#define  XEN_NETTXF_extra_info		(1U<<_XEN_NETTXF_extra_info)
+
+#define XEN_NETIF_MAX_TX_SIZE 0xFFFF
+struct xen_netif_tx_request {
+    grant_ref_t gref;      /* Reference to buffer page */
+    uint16_t offset;       /* Offset within buffer page */
+    uint16_t flags;        /* XEN_NETTXF_* */
+    uint16_t id;           /* Echoed in response message. */
+    uint16_t size;         /* Packet size in bytes.       */
+};
+
+/* Types of xen_netif_extra_info descriptors. */
+#define XEN_NETIF_EXTRA_TYPE_NONE	(0)  /* Never used - invalid */
+#define XEN_NETIF_EXTRA_TYPE_GSO	(1)  /* u.gso */
+#define XEN_NETIF_EXTRA_TYPE_MAX	(2)
+
+/* xen_netif_extra_info flags. */
+#define _XEN_NETIF_EXTRA_FLAG_MORE	(0)
+#define  XEN_NETIF_EXTRA_FLAG_MORE	(1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
+
+/* GSO types */
+#define XEN_NETIF_GSO_TYPE_NONE		(0)
+#define XEN_NETIF_GSO_TYPE_TCPV4	(1)
+#define XEN_NETIF_GSO_TYPE_TCPV6	(2)
+
+/*
+ * This structure needs to fit within both netif_tx_request and
+ * netif_rx_response for compatibility.
+ */
+struct xen_netif_extra_info {
+	uint8_t type;  /* XEN_NETIF_EXTRA_TYPE_* */
+	uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */
+
+	union {
+		struct {
+			/*
+			 * Maximum payload size of each segment. For
+			 * example, for TCP this is just the path MSS.
+			 */
+			uint16_t size;
+
+			/*
+			 * GSO type. This determines the protocol of
+			 * the packet and any extra features required
+			 * to segment the packet properly.
+			 */
+			uint8_t type; /* XEN_NETIF_GSO_TYPE_* */
+
+			/* Future expansion. */
+			uint8_t pad;
+
+			/*
+			 * GSO features. This specifies any extra GSO
+			 * features required to process this packet,
+			 * such as ECN support for TCPv4.
+			 */
+			uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
+		} gso;
+
+		uint16_t pad[3];
+	} u;
+};
+
+struct xen_netif_tx_response {
+	uint16_t id;
+	int16_t  status;       /* XEN_NETIF_RSP_* */
+};
+
+struct xen_netif_rx_request {
+	uint16_t    id;        /* Echoed in response message.        */
+	grant_ref_t gref;      /* Reference to incoming granted frame */
+};
+
+/* Packet data has been validated against protocol checksum. */
+#define _XEN_NETRXF_data_validated	(0)
+#define  XEN_NETRXF_data_validated	(1U<<_XEN_NETRXF_data_validated)
+
+/* Protocol checksum field is blank in the packet (hardware offload)? */
+#define _XEN_NETRXF_csum_blank		(1)
+#define  XEN_NETRXF_csum_blank		(1U<<_XEN_NETRXF_csum_blank)
+
+/* Packet continues in the next request descriptor. */
+#define _XEN_NETRXF_more_data		(2)
+#define  XEN_NETRXF_more_data		(1U<<_XEN_NETRXF_more_data)
+
+/* Packet to be followed by extra descriptor(s). */
+#define _XEN_NETRXF_extra_info		(3)
+#define  XEN_NETRXF_extra_info		(1U<<_XEN_NETRXF_extra_info)
+
+/* GSO Prefix descriptor. */
+#define _XEN_NETRXF_gso_prefix		(4)
+#define  XEN_NETRXF_gso_prefix		(1U<<_XEN_NETRXF_gso_prefix)
+
+struct xen_netif_rx_response {
+    uint16_t id;
+    uint16_t offset;       /* Offset in page of start of received packet  */
+    uint16_t flags;        /* XEN_NETRXF_* */
+    int16_t  status;       /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
+};
+
+/*
+ * Generate netif ring structures and types.
+ */
+
+DEFINE_RING_TYPES(xen_netif_tx,
+		  struct xen_netif_tx_request,
+		  struct xen_netif_tx_response);
+DEFINE_RING_TYPES(xen_netif_rx,
+		  struct xen_netif_rx_request,
+		  struct xen_netif_rx_response);
+
+#define XEN_NETIF_RSP_DROPPED	-2
+#define XEN_NETIF_RSP_ERROR	-1
+#define XEN_NETIF_RSP_OKAY	 0
+/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
+#define XEN_NETIF_RSP_NULL	 1
+
+#endif
diff --git a/kernel/include/xen/interface/io/pciif.h b/kernel/include/xen/interface/io/pciif.h
new file mode 100644
index 000000000..d9922ae36
--- /dev/null
+++ b/kernel/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
diff --git a/kernel/include/xen/interface/io/protocols.h b/kernel/include/xen/interface/io/protocols.h
new file mode 100644
index 000000000..545a14ba0
--- /dev/null
+++ b/kernel/include/xen/interface/io/protocols.h
@@ -0,0 +1,21 @@
+#ifndef __XEN_PROTOCOLS_H__
+#define __XEN_PROTOCOLS_H__
+
+#define XEN_IO_PROTO_ABI_X86_32     "x86_32-abi"
+#define XEN_IO_PROTO_ABI_X86_64     "x86_64-abi"
+#define XEN_IO_PROTO_ABI_POWERPC64  "powerpc64-abi"
+#define XEN_IO_PROTO_ABI_ARM        "arm-abi"
+
+#if defined(__i386__)
+# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32
+#elif defined(__x86_64__)
+# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64
+#elif defined(__powerpc64__)
+# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_POWERPC64
+#elif defined(__arm__) || defined(__aarch64__)
+# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM
+#else
+# error arch fixup needed here
+#endif
+
+#endif
diff --git a/kernel/include/xen/interface/io/ring.h b/kernel/include/xen/interface/io/ring.h
new file mode 100644
index 000000000..7d28aff60
--- /dev/null
+++ b/kernel/include/xen/interface/io/ring.h
@@ -0,0 +1,272 @@
+/******************************************************************************
+ * ring.h
+ *
+ * Shared producer-consumer ring macros.
+ *
+ * Tim Deegan and Andrew Warfield November 2004.
+ */
+
+#ifndef __XEN_PUBLIC_IO_RING_H__
+#define __XEN_PUBLIC_IO_RING_H__
+
+typedef unsigned int RING_IDX;
+
+/* Round a 32-bit unsigned constant down to the nearest power of two. */
+#define __RD2(_x)  (((_x) & 0x00000002) ? 0x2		       : ((_x) & 0x1))
+#define __RD4(_x)  (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2    : __RD2(_x))
+#define __RD8(_x)  (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4    : __RD4(_x))
+#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8    : __RD8(_x))
+#define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x))
+
+/*
+ * Calculate size of a shared ring, given the total available space for the
+ * ring and indexes (_sz), and the name tag of the request/response structure.
+ * A ring contains as many entries as will fit, rounded down to the nearest
+ * power of two (so we can mask with (size-1) to loop around).
+ */
+#define __CONST_RING_SIZE(_s, _sz)				\
+	(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) /	\
+		sizeof(((struct _s##_sring *)0)->ring[0])))
+
+/*
+ * The same for passing in an actual pointer instead of a name tag.
+ */
+#define __RING_SIZE(_s, _sz)						\
+	(__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
+
+/*
+ * Macros to make the correct C datatypes for a new kind of ring.
+ *
+ * To make a new ring datatype, you need to have two message structures,
+ * let's say struct request, and struct response already defined.
+ *
+ * In a header where you want the ring datatype declared, you then do:
+ *
+ *     DEFINE_RING_TYPES(mytag, struct request, struct response);
+ *
+ * These expand out to give you a set of types, as you can see below.
+ * The most important of these are:
+ *
+ *     struct mytag_sring      - The shared ring.
+ *     struct mytag_front_ring - The 'front' half of the ring.
+ *     struct mytag_back_ring  - The 'back' half of the ring.
+ *
+ * To initialize a ring in your code you need to know the location and size
+ * of the shared memory area (PAGE_SIZE, for instance). To initialise
+ * the front half:
+ *
+ *     struct mytag_front_ring front_ring;
+ *     SHARED_RING_INIT((struct mytag_sring *)shared_page);
+ *     FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page,
+ *		       PAGE_SIZE);
+ *
+ * Initializing the back follows similarly (note that only the front
+ * initializes the shared ring):
+ *
+ *     struct mytag_back_ring back_ring;
+ *     BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page,
+ *		      PAGE_SIZE);
+ */
+
+#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t)			\
+									\
+/* Shared ring entry */							\
+union __name##_sring_entry {						\
+    __req_t req;							\
+    __rsp_t rsp;							\
+};									\
+									\
+/* Shared ring page */							\
+struct __name##_sring {							\
+    RING_IDX req_prod, req_event;					\
+    RING_IDX rsp_prod, rsp_event;					\
+    uint8_t  pad[48];							\
+    union __name##_sring_entry ring[1]; /* variable-length */		\
+};									\
+									\
+/* "Front" end's private variables */					\
+struct __name##_front_ring {						\
+    RING_IDX req_prod_pvt;						\
+    RING_IDX rsp_cons;							\
+    unsigned int nr_ents;						\
+    struct __name##_sring *sring;					\
+};									\
+									\
+/* "Back" end's private variables */					\
+struct __name##_back_ring {						\
+    RING_IDX rsp_prod_pvt;						\
+    RING_IDX req_cons;							\
+    unsigned int nr_ents;						\
+    struct __name##_sring *sring;					\
+};
+
+/*
+ * Macros for manipulating rings.
+ *
+ * FRONT_RING_whatever works on the "front end" of a ring: here
+ * requests are pushed on to the ring and responses taken off it.
+ *
+ * BACK_RING_whatever works on the "back end" of a ring: here
+ * requests are taken off the ring and responses put on.
+ *
+ * N.B. these macros do NO INTERLOCKS OR FLOW CONTROL.
+ * This is OK in 1-for-1 request-response situations where the
+ * requestor (front end) never has more than RING_SIZE()-1
+ * outstanding requests.
+ */
+
+/* Initialising empty rings */
+#define SHARED_RING_INIT(_s) do {					\
+    (_s)->req_prod  = (_s)->rsp_prod  = 0;				\
+    (_s)->req_event = (_s)->rsp_event = 1;				\
+    memset((_s)->pad, 0, sizeof((_s)->pad));				\
+} while(0)
+
+#define FRONT_RING_INIT(_r, _s, __size) do {				\
+    (_r)->req_prod_pvt = 0;						\
+    (_r)->rsp_cons = 0;							\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+    (_r)->sring = (_s);							\
+} while (0)
+
+#define BACK_RING_INIT(_r, _s, __size) do {				\
+    (_r)->rsp_prod_pvt = 0;						\
+    (_r)->req_cons = 0;							\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+    (_r)->sring = (_s);							\
+} while (0)
+
+/* Initialize to existing shared indexes -- for recovery */
+#define FRONT_RING_ATTACH(_r, _s, __size) do {				\
+    (_r)->sring = (_s);							\
+    (_r)->req_prod_pvt = (_s)->req_prod;				\
+    (_r)->rsp_cons = (_s)->rsp_prod;					\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+} while (0)
+
+#define BACK_RING_ATTACH(_r, _s, __size) do {				\
+    (_r)->sring = (_s);							\
+    (_r)->rsp_prod_pvt = (_s)->rsp_prod;				\
+    (_r)->req_cons = (_s)->req_prod;					\
+    (_r)->nr_ents = __RING_SIZE(_s, __size);				\
+} while (0)
+
+/* How big is this ring? */
+#define RING_SIZE(_r)							\
+    ((_r)->nr_ents)
+
+/* Number of free requests (for use on front side only). */
+#define RING_FREE_REQUESTS(_r)						\
+    (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons))
+
+/* Test if there is an empty slot available on the front ring.
+ * (This is only meaningful from the front. )
+ */
+#define RING_FULL(_r)							\
+    (RING_FREE_REQUESTS(_r) == 0)
+
+/* Test if there are outstanding messages to be processed on a ring. */
+#define RING_HAS_UNCONSUMED_RESPONSES(_r)				\
+    ((_r)->sring->rsp_prod - (_r)->rsp_cons)
+
+#define RING_HAS_UNCONSUMED_REQUESTS(_r)				\
+    ({									\
+	unsigned int req = (_r)->sring->req_prod - (_r)->req_cons;	\
+	unsigned int rsp = RING_SIZE(_r) -				\
+			   ((_r)->req_cons - (_r)->rsp_prod_pvt);	\
+	req < rsp ? req : rsp;						\
+    })
+
+/* Direct access to individual ring elements, by index. */
+#define RING_GET_REQUEST(_r, _idx)					\
+    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
+
+#define RING_GET_RESPONSE(_r, _idx)					\
+    (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+
+/* Loop termination condition: Would the specified index overflow the ring? */
+#define RING_REQUEST_CONS_OVERFLOW(_r, _cons)				\
+    (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r))
+
+/* Ill-behaved frontend determination: Can there be this many requests? */
+#define RING_REQUEST_PROD_OVERFLOW(_r, _prod)               \
+    (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))
+
+
+#define RING_PUSH_REQUESTS(_r) do {					\
+    wmb(); /* back sees requests /before/ updated producer index */	\
+    (_r)->sring->req_prod = (_r)->req_prod_pvt;				\
+} while (0)
+
+#define RING_PUSH_RESPONSES(_r) do {					\
+    wmb(); /* front sees responses /before/ updated producer index */	\
+    (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt;				\
+} while (0)
+
+/*
+ * Notification hold-off (req_event and rsp_event):
+ *
+ * When queueing requests or responses on a shared ring, it may not always be
+ * necessary to notify the remote end. For example, if requests are in flight
+ * in a backend, the front may be able to queue further requests without
+ * notifying the back (if the back checks for new requests when it queues
+ * responses).
+ *
+ * When enqueuing requests or responses:
+ *
+ *  Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument
+ *  is a boolean return value. True indicates that the receiver requires an
+ *  asynchronous notification.
+ *
+ * After dequeuing requests or responses (before sleeping the connection):
+ *
+ *  Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES().
+ *  The second argument is a boolean return value. True indicates that there
+ *  are pending messages on the ring (i.e., the connection should not be put
+ *  to sleep).
+ *
+ *  These macros will set the req_event/rsp_event field to trigger a
+ *  notification on the very next message that is enqueued. If you want to
+ *  create batches of work (i.e., only receive a notification after several
+ *  messages have been enqueued) then you will need to create a customised
+ *  version of the FINAL_CHECK macro in your own code, which sets the event
+ *  field appropriately.
+ */
+
+#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do {		\
+    RING_IDX __old = (_r)->sring->req_prod;				\
+    RING_IDX __new = (_r)->req_prod_pvt;				\
+    wmb(); /* back sees requests /before/ updated producer index */	\
+    (_r)->sring->req_prod = __new;					\
+    mb(); /* back sees new requests /before/ we check req_event */	\
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) <		\
+		 (RING_IDX)(__new - __old));				\
+} while (0)
+
+#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do {		\
+    RING_IDX __old = (_r)->sring->rsp_prod;				\
+    RING_IDX __new = (_r)->rsp_prod_pvt;				\
+    wmb(); /* front sees responses /before/ updated producer index */	\
+    (_r)->sring->rsp_prod = __new;					\
+    mb(); /* front sees new responses /before/ we check rsp_event */	\
+    (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) <		\
+		 (RING_IDX)(__new - __old));				\
+} while (0)
+
+#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do {		\
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
+    if (_work_to_do) break;						\
+    (_r)->sring->req_event = (_r)->req_cons + 1;			\
+    mb();								\
+    (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r);			\
+} while (0)
+
+#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do {		\
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
+    if (_work_to_do) break;						\
+    (_r)->sring->rsp_event = (_r)->rsp_cons + 1;			\
+    mb();								\
+    (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
+} while (0)
+
+#endif /* __XEN_PUBLIC_IO_RING_H__ */
diff --git a/kernel/include/xen/interface/io/tpmif.h b/kernel/include/xen/interface/io/tpmif.h
new file mode 100644
index 000000000..28e7dcd75
--- /dev/null
+++ b/kernel/include/xen/interface/io/tpmif.h
@@ -0,0 +1,52 @@
+/******************************************************************************
+ * tpmif.h
+ *
+ * TPM I/O interface for Xen guest OSes, v2
+ *
+ * This file is in the public domain.
+ *
+ */
+
+#ifndef __XEN_PUBLIC_IO_TPMIF_H__
+#define __XEN_PUBLIC_IO_TPMIF_H__
+
+/*
+ * Xenbus state machine
+ *
+ * Device open:
+ *   1. Both ends start in XenbusStateInitialising
+ *   2. Backend transitions to InitWait (frontend does not wait on this step)
+ *   3. Frontend populates ring-ref, event-channel, feature-protocol-v2
+ *   4. Frontend transitions to Initialised
+ *   5. Backend maps grant and event channel, verifies feature-protocol-v2
+ *   6. Backend transitions to Connected
+ *   7. Frontend verifies feature-protocol-v2, transitions to Connected
+ *
+ * Device close:
+ *   1. State is changed to XenbusStateClosing
+ *   2. Frontend transitions to Closed
+ *   3. Backend unmaps grant and event, changes state to InitWait
+ */
+
+enum vtpm_shared_page_state {
+	VTPM_STATE_IDLE,         /* no contents / vTPM idle / cancel complete */
+	VTPM_STATE_SUBMIT,       /* request ready / vTPM working */
+	VTPM_STATE_FINISH,       /* response ready / vTPM idle */
+	VTPM_STATE_CANCEL,       /* cancel requested / vTPM working */
+};
+/* The backend should only change state to IDLE or FINISH, while the
+ * frontend should only change to SUBMIT or CANCEL. */
+
+
+struct vtpm_shared_page {
+	uint32_t length;         /* request/response length in bytes */
+
+	uint8_t state;           /* enum vtpm_shared_page_state */
+	uint8_t locality;        /* for the current request */
+	uint8_t pad;
+
+	uint8_t nr_extra_pages;  /* extra pages for long packets; may be zero */
+	uint32_t extra_pages[0]; /* grant IDs; length in nr_extra_pages */
+};
+
+#endif
diff --git a/kernel/include/xen/interface/io/vscsiif.h b/kernel/include/xen/interface/io/vscsiif.h
new file mode 100644
index 000000000..d07d7aca8
--- /dev/null
+++ b/kernel/include/xen/interface/io/vscsiif.h
@@ -0,0 +1,229 @@
+/******************************************************************************
+ * vscsiif.h
+ *
+ * Based on the blkif.h code.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright(c) FUJITSU Limited 2008.
+ */
+
+#ifndef __XEN__PUBLIC_IO_SCSI_H__
+#define __XEN__PUBLIC_IO_SCSI_H__
+
+#include "ring.h"
+#include "../grant_table.h"
+
+/*
+ * Feature and Parameter Negotiation
+ * =================================
+ * The two halves of a Xen pvSCSI driver utilize nodes within the XenStore to
+ * communicate capabilities and to negotiate operating parameters.  This
+ * section enumerates these nodes which reside in the respective front and
+ * backend portions of the XenStore, following the XenBus convention.
+ *
+ * Any specified default value is in effect if the corresponding XenBus node
+ * is not present in the XenStore.
+ *
+ * XenStore nodes in sections marked "PRIVATE" are solely for use by the
+ * driver side whose XenBus tree contains them.
+ *
+ *****************************************************************************
+ *                            Backend XenBus Nodes
+ *****************************************************************************
+ *
+ *------------------ Backend Device Identification (PRIVATE) ------------------
+ *
+ * p-devname
+ *      Values:         string
+ *
+ *      A free string used to identify the physical device (e.g. a disk name).
+ *
+ * p-dev
+ *      Values:         string
+ *
+ *      A string specifying the backend device: either a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers), or a WWN (e.g.
+ *      "naa.60014054ac780582").
+ *
+ * v-dev
+ *      Values:         string
+ *
+ *      A string specifying the frontend device in form of a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers).
+ *
+ *--------------------------------- Features ---------------------------------
+ *
+ * feature-sg-grant
+ *      Values:         unsigned [VSCSIIF_SG_TABLESIZE...65535]
+ *      Default Value:  0
+ *
+ *      Specifies the maximum number of scatter/gather elements in grant pages
+ *      supported. If not set, the backend supports up to VSCSIIF_SG_TABLESIZE
+ *      SG elements specified directly in the request.
+ *
+ *****************************************************************************
+ *                            Frontend XenBus Nodes
+ *****************************************************************************
+ *
+ *----------------------- Request Transport Parameters -----------------------
+ *
+ * event-channel
+ *      Values:         unsigned
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * ring-ref
+ *      Values:         unsigned
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      the sole page in a single page sized ring buffer.
+ *
+ * protocol
+ *      Values:         string (XEN_IO_PROTO_ABI_*)
+ *      Default Value:  XEN_IO_PROTO_ABI_NATIVE
+ *
+ *      The machine ABI rules governing the format of all ring request and
+ *      response structures.
+ */
+
+/* Requests from the frontend to the backend */
+
+/*
+ * Request a SCSI operation specified via a CDB in vscsiif_request.cmnd.
+ * The target is specified via channel, id and lun.
+ *
+ * The operation to be performed is specified via a CDB in cmnd[], the length
+ * of the CDB is in cmd_len. sc_data_direction specifies the direction of data
+ * (to the device, from the device, or none at all).
+ *
+ * If data is to be transferred to or from the device the buffer(s) in the
+ * guest memory is/are specified via one or multiple scsiif_request_segment
+ * descriptors each specifying a memory page via a grant_ref_t, a offset into
+ * the page and the length of the area in that page. All scsiif_request_segment
+ * areas concatenated form the resulting data buffer used by the operation.
+ * If the number of scsiif_request_segment areas is not too large (less than
+ * or equal VSCSIIF_SG_TABLESIZE) the areas can be specified directly in the
+ * seg[] array and the number of valid scsiif_request_segment elements is to be
+ * set in nr_segments.
+ *
+ * If "feature-sg-grant" in the Xenstore is set it is possible to specify more
+ * than VSCSIIF_SG_TABLESIZE scsiif_request_segment elements via indirection.
+ * The maximum number of allowed scsiif_request_segment elements is the value
+ * of the "feature-sg-grant" entry from Xenstore. When using indirection the
+ * seg[] array doesn't contain specifications of the data buffers, but
+ * references to scsiif_request_segment arrays, which in turn reference the
+ * data buffers. While nr_segments holds the number of populated seg[] entries
+ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment
+ * elements referencing the target data buffers is calculated from the lengths
+ * of the seg[] elements (the sum of all valid seg[].length divided by the
+ * size of one scsiif_request_segment structure).
+ */
+#define VSCSIIF_ACT_SCSI_CDB		1
+
+/*
+ * Request abort of a running operation for the specified target given by
+ * channel, id, lun and the operation's rqid in ref_rqid.
+ */
+#define VSCSIIF_ACT_SCSI_ABORT		2
+
+/*
+ * Request a device reset of the specified target (channel and id).
+ */
+#define VSCSIIF_ACT_SCSI_RESET		3
+
+/*
+ * Preset scatter/gather elements for a following request. Deprecated.
+ * Keeping the define only to avoid usage of the value "4" for other actions.
+ */
+#define VSCSIIF_ACT_SCSI_SG_PRESET	4
+
+/*
+ * Maximum scatter/gather segments per request.
+ *
+ * Considering balance between allocating at least 16 "vscsiif_request"
+ * structures on one page (4096 bytes) and the number of scatter/gather
+ * elements needed, we decided to use 26 as a magic number.
+ *
+ * If "feature-sg-grant" is set, more scatter/gather elements can be specified
+ * by placing them in one or more (up to VSCSIIF_SG_TABLESIZE) granted pages.
+ * In this case the vscsiif_request seg elements don't contain references to
+ * the user data, but to the SG elements referencing the user data.
+ */
+#define VSCSIIF_SG_TABLESIZE		26
+
+/*
+ * based on Linux kernel 2.6.18, still valid
+ * Changing these values requires support of multiple protocols via the rings
+ * as "old clients" will blindly use these values and the resulting structure
+ * sizes.
+ */
+#define VSCSIIF_MAX_COMMAND_SIZE	16
+#define VSCSIIF_SENSE_BUFFERSIZE	96
+
+struct scsiif_request_segment {
+	grant_ref_t gref;
+	uint16_t offset;
+	uint16_t length;
+};
+
+#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment))
+
+/* Size of one request is 252 bytes */
+struct vscsiif_request {
+	uint16_t rqid;		/* private guest value, echoed in resp  */
+	uint8_t act;		/* command between backend and frontend */
+	uint8_t cmd_len;	/* valid CDB bytes */
+
+	uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE];	/* the CDB */
+	uint16_t timeout_per_command;	/* deprecated */
+	uint16_t channel, id, lun;	/* (virtual) device specification */
+	uint16_t ref_rqid;		/* command abort reference */
+	uint8_t sc_data_direction;	/* for DMA_TO_DEVICE(1)
+					   DMA_FROM_DEVICE(2)
+					   DMA_NONE(3) requests */
+	uint8_t nr_segments;		/* Number of pieces of scatter-gather */
+/*
+ * flag in nr_segments: SG elements via grant page
+ *
+ * If VSCSIIF_SG_GRANT is set, the low 7 bits of nr_segments specify the number
+ * of grant pages containing SG elements. Usable if "feature-sg-grant" set.
+ */
+#define VSCSIIF_SG_GRANT	0x80
+
+	struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE];
+	uint32_t reserved[3];
+};
+
+/* Size of one response is 252 bytes */
+struct vscsiif_response {
+	uint16_t rqid;		/* identifies request */
+	uint8_t padding;
+	uint8_t sense_len;
+	uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE];
+	int32_t rslt;
+	uint32_t residual_len;	/* request bufflen -
+				   return the value from physical device */
+	uint32_t reserved[36];
+};
+
+DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response);
+
+#endif /*__XEN__PUBLIC_IO_SCSI_H__*/
diff --git a/kernel/include/xen/interface/io/xenbus.h b/kernel/include/xen/interface/io/xenbus.h
new file mode 100644
index 000000000..9fda53297
--- /dev/null
+++ b/kernel/include/xen/interface/io/xenbus.h
@@ -0,0 +1,50 @@
+/*****************************************************************************
+ * xenbus.h
+ *
+ * Xenbus protocol details.
+ *
+ * Copyright (C) 2005 XenSource Ltd.
+ */
+
+#ifndef _XEN_PUBLIC_IO_XENBUS_H
+#define _XEN_PUBLIC_IO_XENBUS_H
+
+/* The state of either end of the Xenbus, i.e. the current communication
+   status of initialisation across the bus.  States here imply nothing about
+   the state of the connection between the driver and the kernel's device
+   layers.  */
+enum xenbus_state
+{
+	XenbusStateUnknown      = 0,
+	XenbusStateInitialising = 1,
+	XenbusStateInitWait     = 2,  /* Finished early
+					 initialisation, but waiting
+					 for information from the peer
+					 or hotplug scripts. */
+	XenbusStateInitialised  = 3,  /* Initialised and waiting for a
+					 connection from the peer. */
+	XenbusStateConnected    = 4,
+	XenbusStateClosing      = 5,  /* The device is being closed
+					 due to an error or an unplug
+					 event. */
+	XenbusStateClosed       = 6,
+
+	/*
+	* Reconfiguring: The device is being reconfigured.
+	*/
+	XenbusStateReconfiguring = 7,
+
+	XenbusStateReconfigured  = 8
+};
+
+#endif /* _XEN_PUBLIC_IO_XENBUS_H */
+
+/*
+ * Local variables:
+ *  c-file-style: "linux"
+ *  indent-tabs-mode: t
+ *  c-indent-level: 8
+ *  c-basic-offset: 8
+ *  tab-width: 8
+ * End:
+ */
diff --git a/kernel/include/xen/interface/io/xs_wire.h b/kernel/include/xen/interface/io/xs_wire.h
new file mode 100644
index 000000000..794deb07e
--- /dev/null
+++ b/kernel/include/xen/interface/io/xs_wire.h
@@ -0,0 +1,94 @@
+/*
+ * Details of the "wire" protocol between Xen Store Daemon and client
+ * library or guest kernel.
+ * Copyright (C) 2005 Rusty Russell IBM Corporation
+ */
+
+#ifndef _XS_WIRE_H
+#define _XS_WIRE_H
+
+enum xsd_sockmsg_type
+{
+    XS_DEBUG,
+    XS_DIRECTORY,
+    XS_READ,
+    XS_GET_PERMS,
+    XS_WATCH,
+    XS_UNWATCH,
+    XS_TRANSACTION_START,
+    XS_TRANSACTION_END,
+    XS_INTRODUCE,
+    XS_RELEASE,
+    XS_GET_DOMAIN_PATH,
+    XS_WRITE,
+    XS_MKDIR,
+    XS_RM,
+    XS_SET_PERMS,
+    XS_WATCH_EVENT,
+    XS_ERROR,
+    XS_IS_DOMAIN_INTRODUCED,
+    XS_RESUME,
+    XS_SET_TARGET,
+    XS_RESTRICT,
+    XS_RESET_WATCHES,
+};
+
+#define XS_WRITE_NONE "NONE"
+#define XS_WRITE_CREATE "CREATE"
+#define XS_WRITE_CREATE_EXCL "CREATE|EXCL"
+
+/* We hand errors as strings, for portability. */
+struct xsd_errors
+{
+    int errnum;
+    const char *errstring;
+};
+#define XSD_ERROR(x) { x, #x }
+static struct xsd_errors xsd_errors[] __attribute__((unused)) = {
+    XSD_ERROR(EINVAL),
+    XSD_ERROR(EACCES),
+    XSD_ERROR(EEXIST),
+    XSD_ERROR(EISDIR),
+    XSD_ERROR(ENOENT),
+    XSD_ERROR(ENOMEM),
+    XSD_ERROR(ENOSPC),
+    XSD_ERROR(EIO),
+    XSD_ERROR(ENOTEMPTY),
+    XSD_ERROR(ENOSYS),
+    XSD_ERROR(EROFS),
+    XSD_ERROR(EBUSY),
+    XSD_ERROR(EAGAIN),
+    XSD_ERROR(EISCONN)
+};
+
+struct xsd_sockmsg
+{
+    uint32_t type;  /* XS_??? */
+    uint32_t req_id;/* Request identifier, echoed in daemon's response.  */
+    uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */
+    uint32_t len;   /* Length of data following this. */
+
+    /* Generally followed by nul-terminated string(s). */
+};
+
+enum xs_watch_type
+{
+    XS_WATCH_PATH = 0,
+    XS_WATCH_TOKEN
+};
+
+/* Inter-domain shared memory communications. */
+#define XENSTORE_RING_SIZE 1024
+typedef uint32_t XENSTORE_RING_IDX;
+#define MASK_XENSTORE_IDX(idx) ((idx) & (XENSTORE_RING_SIZE-1))
+struct xenstore_domain_interface {
+    char req[XENSTORE_RING_SIZE]; /* Requests to xenstore daemon. */
+    char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */
+    XENSTORE_RING_IDX req_cons, req_prod;
+    XENSTORE_RING_IDX rsp_cons, rsp_prod;
+};
+
+/* Violating this is very bad.  See docs/misc/xenstore.txt. */
+#define XENSTORE_PAYLOAD_MAX 4096
+
+#endif /* _XS_WIRE_H */
diff --git a/kernel/include/xen/interface/memory.h b/kernel/include/xen/interface/memory.h
new file mode 100644
index 000000000..2ecfe4f70
--- /dev/null
+++ b/kernel/include/xen/interface/memory.h
@@ -0,0 +1,266 @@
+/******************************************************************************
+ * memory.h
+ *
+ * Memory reservation and information.
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_MEMORY_H__
+#define __XEN_PUBLIC_MEMORY_H__
+
+#include <linux/spinlock.h>
+
+/*
+ * Increase or decrease the specified domain's memory reservation. Returns a
+ * -ve errcode on failure, or the # extents successfully allocated or freed.
+ * arg == addr of struct xen_memory_reservation.
+ */
+#define XENMEM_increase_reservation 0
+#define XENMEM_decrease_reservation 1
+#define XENMEM_populate_physmap     6
+struct xen_memory_reservation {
+
+    /*
+     * XENMEM_increase_reservation:
+     *   OUT: MFN (*not* GMFN) bases of extents that were allocated
+     * XENMEM_decrease_reservation:
+     *   IN:  GMFN bases of extents to free
+     * XENMEM_populate_physmap:
+     *   IN:  GPFN bases of extents to populate with memory
+     *   OUT: GMFN bases of extents that were allocated
+     *   (NB. This command also updates the mach_to_phys translation table)
+     */
+    GUEST_HANDLE(xen_pfn_t) extent_start;
+
+    /* Number of extents, and size/alignment of each (2^extent_order pages). */
+    xen_ulong_t  nr_extents;
+    unsigned int   extent_order;
+
+    /*
+     * Maximum # bits addressable by the user of the allocated region (e.g.,
+     * I/O devices often have a 32-bit limitation even in 64-bit systems). If
+     * zero then the user has no addressing restriction.
+     * This field is not used by XENMEM_decrease_reservation.
+     */
+    unsigned int   address_bits;
+
+    /*
+     * Domain whose reservation is being changed.
+     * Unprivileged domains can specify only DOMID_SELF.
+     */
+    domid_t        domid;
+
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation);
+
+/*
+ * An atomic exchange of memory pages. If return code is zero then
+ * @out.extent_list provides GMFNs of the newly-allocated memory.
+ * Returns zero on complete success, otherwise a negative error code.
+ * On complete success then always @nr_exchanged == @in.nr_extents.
+ * On partial success @nr_exchanged indicates how much work was done.
+ */
+#define XENMEM_exchange             11
+struct xen_memory_exchange {
+    /*
+     * [IN] Details of memory extents to be exchanged (GMFN bases).
+     * Note that @in.address_bits is ignored and unused.
+     */
+    struct xen_memory_reservation in;
+
+    /*
+     * [IN/OUT] Details of new memory extents.
+     * We require that:
+     *  1. @in.domid == @out.domid
+     *  2. @in.nr_extents  << @in.extent_order ==
+     *     @out.nr_extents << @out.extent_order
+     *  3. @in.extent_start and @out.extent_start lists must not overlap
+     *  4. @out.extent_start lists GPFN bases to be populated
+     *  5. @out.extent_start is overwritten with allocated GMFN bases
+     */
+    struct xen_memory_reservation out;
+
+    /*
+     * [OUT] Number of input extents that were successfully exchanged:
+     *  1. The first @nr_exchanged input extents were successfully
+     *     deallocated.
+     *  2. The corresponding first entries in the output extent list correctly
+     *     indicate the GMFNs that were successfully exchanged.
+     *  3. All other input and output extents are untouched.
+     *  4. If not all input exents are exchanged then the return code of this
+     *     command will be non-zero.
+     *  5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER!
+     */
+    xen_ulong_t nr_exchanged;
+};
+
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_exchange);
+/*
+ * Returns the maximum machine frame number of mapped RAM in this system.
+ * This command always succeeds (it never returns an error code).
+ * arg == NULL.
+ */
+#define XENMEM_maximum_ram_page     2
+
+/*
+ * Returns the current or maximum memory reservation, in pages, of the
+ * specified domain (may be DOMID_SELF). Returns -ve errcode on failure.
+ * arg == addr of domid_t.
+ */
+#define XENMEM_current_reservation  3
+#define XENMEM_maximum_reservation  4
+
+/*
+ * Returns a list of MFN bases of 2MB extents comprising the machine_to_phys
+ * mapping table. Architectures which do not have a m2p table do not implement
+ * this command.
+ * arg == addr of xen_machphys_mfn_list_t.
+ */
+#define XENMEM_machphys_mfn_list    5
+struct xen_machphys_mfn_list {
+    /*
+     * Size of the 'extent_start' array. Fewer entries will be filled if the
+     * machphys table is smaller than max_extents * 2MB.
+     */
+    unsigned int max_extents;
+
+    /*
+     * Pointer to buffer to fill with list of extent starts. If there are
+     * any large discontiguities in the machine address space, 2MB gaps in
+     * the machphys table will be represented by an MFN base of zero.
+     */
+    GUEST_HANDLE(xen_pfn_t) extent_start;
+
+    /*
+     * Number of extents written to the above array. This will be smaller
+     * than 'max_extents' if the machphys table is smaller than max_e * 2MB.
+     */
+    unsigned int nr_extents;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mfn_list);
+
+/*
+ * Returns the location in virtual address space of the machine_to_phys
+ * mapping table. Architectures which do not have a m2p table, or which do not
+ * map it by default into guest address space, do not implement this command.
+ * arg == addr of xen_machphys_mapping_t.
+ */
+#define XENMEM_machphys_mapping     12
+struct xen_machphys_mapping {
+    xen_ulong_t v_start, v_end; /* Start and end virtual addresses.   */
+    xen_ulong_t max_mfn;        /* Maximum MFN that can be looked up. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t);
+
+#define XENMAPSPACE_shared_info  0 /* shared info page */
+#define XENMAPSPACE_grant_table  1 /* grant table page */
+#define XENMAPSPACE_gmfn         2 /* GMFN */
+#define XENMAPSPACE_gmfn_range   3 /* GMFN range, XENMEM_add_to_physmap only. */
+#define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom,
+				    * XENMEM_add_to_physmap_range only.
+				    */
+
+/*
+ * Sets the GPFN at which a particular page appears in the specified guest's
+ * pseudophysical address space.
+ * arg == addr of xen_add_to_physmap_t.
+ */
+#define XENMEM_add_to_physmap      7
+struct xen_add_to_physmap {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+
+    /* Number of pages to go through for gmfn_range */
+    uint16_t    size;
+
+    /* Source mapping space. */
+    unsigned int space;
+
+    /* Index into source mapping space. */
+    xen_ulong_t idx;
+
+    /* GPFN where the source mapping page should appear. */
+    xen_pfn_t gpfn;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap);
+
+/*** REMOVED ***/
+/*#define XENMEM_translate_gpfn_list  8*/
+
+#define XENMEM_add_to_physmap_range 23
+struct xen_add_to_physmap_range {
+    /* IN */
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+    uint16_t space; /* => enum phys_map_space */
+
+    /* Number of pages to go through */
+    uint16_t size;
+    domid_t foreign_domid; /* IFF gmfn_foreign */
+
+    /* Indexes into space being mapped. */
+    GUEST_HANDLE(xen_ulong_t) idxs;
+
+    /* GPFN in domid where the source mapping page should appear. */
+    GUEST_HANDLE(xen_pfn_t) gpfns;
+
+    /* OUT */
+
+    /* Per index error code. */
+    GUEST_HANDLE(int) errs;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap_range);
+
+/*
+ * Returns the pseudo-physical memory map as it was when the domain
+ * was started (specified by XENMEM_set_memory_map).
+ * arg == addr of struct xen_memory_map.
+ */
+#define XENMEM_memory_map           9
+struct xen_memory_map {
+    /*
+     * On call the number of entries which can be stored in buffer. On
+     * return the number of entries which have been stored in
+     * buffer.
+     */
+    unsigned int nr_entries;
+
+    /*
+     * Entries in the buffer are in the same format as returned by the
+     * BIOS INT 0x15 EAX=0xE820 call.
+     */
+    GUEST_HANDLE(void) buffer;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_map);
+
+/*
+ * Returns the real physical memory map. Passes the same structure as
+ * XENMEM_memory_map.
+ * arg == addr of struct xen_memory_map.
+ */
+#define XENMEM_machine_memory_map   10
+
+
+/*
+ * Prevent the balloon driver from changing the memory reservation
+ * during a driver critical region.
+ */
+extern spinlock_t xen_reservation_lock;
+
+/*
+ * Unmaps the page appearing at a particular GPFN from the specified guest's
+ * pseudophysical address space.
+ * arg == addr of xen_remove_from_physmap_t.
+ */
+#define XENMEM_remove_from_physmap      15
+struct xen_remove_from_physmap {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+
+    /* GPFN of the current mapping of the page. */
+    xen_pfn_t gpfn;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_remove_from_physmap);
+
+#endif /* __XEN_PUBLIC_MEMORY_H__ */
diff --git a/kernel/include/xen/interface/nmi.h b/kernel/include/xen/interface/nmi.h
new file mode 100644
index 000000000..b47d9d06f
--- /dev/null
+++ b/kernel/include/xen/interface/nmi.h
@@ -0,0 +1,51 @@
+/******************************************************************************
+ * nmi.h
+ *
+ * NMI callback registration and reason codes.
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_NMI_H__
+#define __XEN_PUBLIC_NMI_H__
+
+#include <xen/interface/xen.h>
+
+/*
+ * NMI reason codes:
+ * Currently these are x86-specific, stored in arch_shared_info.nmi_reason.
+ */
+ /* I/O-check error reported via ISA port 0x61, bit 6. */
+#define _XEN_NMIREASON_io_error     0
+#define XEN_NMIREASON_io_error      (1UL << _XEN_NMIREASON_io_error)
+ /* PCI SERR reported via ISA port 0x61, bit 7. */
+#define _XEN_NMIREASON_pci_serr     1
+#define XEN_NMIREASON_pci_serr      (1UL << _XEN_NMIREASON_pci_serr)
+ /* Unknown hardware-generated NMI. */
+#define _XEN_NMIREASON_unknown      2
+#define XEN_NMIREASON_unknown       (1UL << _XEN_NMIREASON_unknown)
+
+/*
+ * long nmi_op(unsigned int cmd, void *arg)
+ * NB. All ops return zero on success, else a negative error code.
+ */
+
+/*
+ * Register NMI callback for this (calling) VCPU. Currently this only makes
+ * sense for domain 0, vcpu 0. All other callers will be returned EINVAL.
+ * arg == pointer to xennmi_callback structure.
+ */
+#define XENNMI_register_callback   0
+struct xennmi_callback {
+    unsigned long handler_address;
+    unsigned long pad;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xennmi_callback);
+
+/*
+ * Deregister NMI callback for this (calling) VCPU.
+ * arg == NULL.
+ */
+#define XENNMI_unregister_callback 1
+
+#endif /* __XEN_PUBLIC_NMI_H__ */
diff --git a/kernel/include/xen/interface/physdev.h b/kernel/include/xen/interface/physdev.h
new file mode 100644
index 000000000..610dba9b6
--- /dev/null
+++ b/kernel/include/xen/interface/physdev.h
@@ -0,0 +1,321 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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 __XEN_PUBLIC_PHYSDEV_H__
+#define __XEN_PUBLIC_PHYSDEV_H__
+
+/*
+ * Prototype for this hypercall is:
+ *  int physdev_op(int cmd, void *args)
+ * @cmd	 == PHYSDEVOP_??? (physdev operation).
+ * @args == Operation-specific extra arguments (NULL if none).
+ */
+
+/*
+ * Notify end-of-interrupt (EOI) for the specified IRQ.
+ * @arg == pointer to physdev_eoi structure.
+ */
+#define PHYSDEVOP_eoi			12
+struct physdev_eoi {
+	/* IN */
+	uint32_t irq;
+};
+
+/*
+ * Register a shared page for the hypervisor to indicate whether the guest
+ * must issue PHYSDEVOP_eoi. The semantics of PHYSDEVOP_eoi change slightly
+ * once the guest used this function in that the associated event channel
+ * will automatically get unmasked. The page registered is used as a bit
+ * array indexed by Xen's PIRQ value.
+ */
+#define PHYSDEVOP_pirq_eoi_gmfn_v1       17
+/*
+ * Register a shared page for the hypervisor to indicate whether the
+ * guest must issue PHYSDEVOP_eoi. This hypercall is very similar to
+ * PHYSDEVOP_pirq_eoi_gmfn_v1 but it doesn't change the semantics of
+ * PHYSDEVOP_eoi. The page registered is used as a bit array indexed by
+ * Xen's PIRQ value.
+ */
+#define PHYSDEVOP_pirq_eoi_gmfn_v2       28
+struct physdev_pirq_eoi_gmfn {
+    /* IN */
+    xen_ulong_t gmfn;
+};
+
+/*
+ * Query the status of an IRQ line.
+ * @arg == pointer to physdev_irq_status_query structure.
+ */
+#define PHYSDEVOP_irq_status_query	 5
+struct physdev_irq_status_query {
+	/* IN */
+	uint32_t irq;
+	/* OUT */
+	uint32_t flags; /* XENIRQSTAT_* */
+};
+
+/* Need to call PHYSDEVOP_eoi when the IRQ has been serviced? */
+#define _XENIRQSTAT_needs_eoi	(0)
+#define	 XENIRQSTAT_needs_eoi	(1U<<_XENIRQSTAT_needs_eoi)
+
+/* IRQ shared by multiple guests? */
+#define _XENIRQSTAT_shared	(1)
+#define	 XENIRQSTAT_shared	(1U<<_XENIRQSTAT_shared)
+
+/*
+ * Set the current VCPU's I/O privilege level.
+ * @arg == pointer to physdev_set_iopl structure.
+ */
+#define PHYSDEVOP_set_iopl		 6
+struct physdev_set_iopl {
+	/* IN */
+	uint32_t iopl;
+};
+
+/*
+ * Set the current VCPU's I/O-port permissions bitmap.
+ * @arg == pointer to physdev_set_iobitmap structure.
+ */
+#define PHYSDEVOP_set_iobitmap		 7
+struct physdev_set_iobitmap {
+	/* IN */
+	uint8_t * bitmap;
+	uint32_t nr_ports;
+};
+
+/*
+ * Read or write an IO-APIC register.
+ * @arg == pointer to physdev_apic structure.
+ */
+#define PHYSDEVOP_apic_read		 8
+#define PHYSDEVOP_apic_write		 9
+struct physdev_apic {
+	/* IN */
+	unsigned long apic_physbase;
+	uint32_t reg;
+	/* IN or OUT */
+	uint32_t value;
+};
+
+/*
+ * Allocate or free a physical upcall vector for the specified IRQ line.
+ * @arg == pointer to physdev_irq structure.
+ */
+#define PHYSDEVOP_alloc_irq_vector	10
+#define PHYSDEVOP_free_irq_vector	11
+struct physdev_irq {
+	/* IN */
+	uint32_t irq;
+	/* IN or OUT */
+	uint32_t vector;
+};
+
+#define MAP_PIRQ_TYPE_MSI		0x0
+#define MAP_PIRQ_TYPE_GSI		0x1
+#define MAP_PIRQ_TYPE_UNKNOWN		0x2
+#define MAP_PIRQ_TYPE_MSI_SEG		0x3
+#define MAP_PIRQ_TYPE_MULTI_MSI		0x4
+
+#define PHYSDEVOP_map_pirq		13
+struct physdev_map_pirq {
+    domid_t domid;
+    /* IN */
+    int type;
+    /* IN */
+    int index;
+    /* IN or OUT */
+    int pirq;
+    /* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */
+    int bus;
+    /* IN */
+    int devfn;
+    /* IN
+     * - For MSI-X contains entry number.
+     * - For MSI with ..._MULTI_MSI contains number of vectors.
+     * OUT (..._MULTI_MSI only)
+     * - Number of vectors allocated.
+     */
+    int entry_nr;
+    /* IN */
+    uint64_t table_base;
+};
+
+#define PHYSDEVOP_unmap_pirq		14
+struct physdev_unmap_pirq {
+    domid_t domid;
+    /* IN */
+    int pirq;
+};
+
+#define PHYSDEVOP_manage_pci_add	15
+#define PHYSDEVOP_manage_pci_remove	16
+struct physdev_manage_pci {
+	/* IN */
+	uint8_t bus;
+	uint8_t devfn;
+};
+
+#define PHYSDEVOP_restore_msi            19
+struct physdev_restore_msi {
+	/* IN */
+	uint8_t bus;
+	uint8_t devfn;
+};
+
+#define PHYSDEVOP_manage_pci_add_ext	20
+struct physdev_manage_pci_ext {
+	/* IN */
+	uint8_t bus;
+	uint8_t devfn;
+	unsigned is_extfn;
+	unsigned is_virtfn;
+	struct {
+		uint8_t bus;
+		uint8_t devfn;
+	} physfn;
+};
+
+/*
+ * Argument to physdev_op_compat() hypercall. Superceded by new physdev_op()
+ * hypercall since 0x00030202.
+ */
+struct physdev_op {
+	uint32_t cmd;
+	union {
+		struct physdev_irq_status_query	     irq_status_query;
+		struct physdev_set_iopl		     set_iopl;
+		struct physdev_set_iobitmap	     set_iobitmap;
+		struct physdev_apic		     apic_op;
+		struct physdev_irq		     irq_op;
+	} u;
+};
+
+#define PHYSDEVOP_setup_gsi    21
+struct physdev_setup_gsi {
+    int gsi;
+    /* IN */
+    uint8_t triggering;
+    /* IN */
+    uint8_t polarity;
+    /* IN */
+};
+
+#define PHYSDEVOP_get_nr_pirqs    22
+struct physdev_nr_pirqs {
+    /* OUT */
+    uint32_t nr_pirqs;
+};
+
+/* type is MAP_PIRQ_TYPE_GSI or MAP_PIRQ_TYPE_MSI
+ * the hypercall returns a free pirq */
+#define PHYSDEVOP_get_free_pirq    23
+struct physdev_get_free_pirq {
+    /* IN */ 
+    int type;
+    /* OUT */
+    uint32_t pirq;
+};
+
+#define XEN_PCI_DEV_EXTFN              0x1
+#define XEN_PCI_DEV_VIRTFN             0x2
+#define XEN_PCI_DEV_PXM                0x4
+
+#define XEN_PCI_MMCFG_RESERVED         0x1
+
+#define PHYSDEVOP_pci_mmcfg_reserved    24
+struct physdev_pci_mmcfg_reserved {
+    uint64_t address;
+    uint16_t segment;
+    uint8_t start_bus;
+    uint8_t end_bus;
+    uint32_t flags;
+};
+
+#define PHYSDEVOP_pci_device_add        25
+struct physdev_pci_device_add {
+    /* IN */
+    uint16_t seg;
+    uint8_t bus;
+    uint8_t devfn;
+    uint32_t flags;
+    struct {
+        uint8_t bus;
+        uint8_t devfn;
+    } physfn;
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+    uint32_t optarr[];
+#elif defined(__GNUC__)
+    uint32_t optarr[0];
+#endif
+};
+
+#define PHYSDEVOP_pci_device_remove     26
+#define PHYSDEVOP_restore_msi_ext       27
+/*
+ * Dom0 should use these two to announce MMIO resources assigned to
+ * MSI-X capable devices won't (prepare) or may (release) change.
+ */
+#define PHYSDEVOP_prepare_msix          30
+#define PHYSDEVOP_release_msix          31
+struct physdev_pci_device {
+    /* IN */
+    uint16_t seg;
+    uint8_t bus;
+    uint8_t devfn;
+};
+
+#define PHYSDEVOP_DBGP_RESET_PREPARE    1
+#define PHYSDEVOP_DBGP_RESET_DONE       2
+
+#define PHYSDEVOP_DBGP_BUS_UNKNOWN      0
+#define PHYSDEVOP_DBGP_BUS_PCI          1
+
+#define PHYSDEVOP_dbgp_op               29
+struct physdev_dbgp_op {
+    /* IN */
+    uint8_t op;
+    uint8_t bus;
+    union {
+        struct physdev_pci_device pci;
+    } u;
+};
+
+/*
+ * Notify that some PIRQ-bound event channels have been unmasked.
+ * ** This command is obsolete since interface version 0x00030202 and is **
+ * ** unsupported by newer versions of Xen.				 **
+ */
+#define PHYSDEVOP_IRQ_UNMASK_NOTIFY	 4
+
+/*
+ * These all-capitals physdev operation names are superceded by the new names
+ * (defined above) since interface version 0x00030202.
+ */
+#define PHYSDEVOP_IRQ_STATUS_QUERY	 PHYSDEVOP_irq_status_query
+#define PHYSDEVOP_SET_IOPL		 PHYSDEVOP_set_iopl
+#define PHYSDEVOP_SET_IOBITMAP		 PHYSDEVOP_set_iobitmap
+#define PHYSDEVOP_APIC_READ		 PHYSDEVOP_apic_read
+#define PHYSDEVOP_APIC_WRITE		 PHYSDEVOP_apic_write
+#define PHYSDEVOP_ASSIGN_VECTOR		 PHYSDEVOP_alloc_irq_vector
+#define PHYSDEVOP_FREE_VECTOR		 PHYSDEVOP_free_irq_vector
+#define PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY XENIRQSTAT_needs_eoi
+#define PHYSDEVOP_IRQ_SHARED		 XENIRQSTAT_shared
+
+#endif /* __XEN_PUBLIC_PHYSDEV_H__ */
diff --git a/kernel/include/xen/interface/platform.h b/kernel/include/xen/interface/platform.h
new file mode 100644
index 000000000..5cc49ea8d
--- /dev/null
+++ b/kernel/include/xen/interface/platform.h
@@ -0,0 +1,503 @@
+/******************************************************************************
+ * platform.h
+ *
+ * Hardware platform operations. Intended for use by domain-0 kernel.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2002-2006, K Fraser
+ */
+
+#ifndef __XEN_PUBLIC_PLATFORM_H__
+#define __XEN_PUBLIC_PLATFORM_H__
+
+#include <xen/interface/xen.h>
+
+#define XENPF_INTERFACE_VERSION 0x03000001
+
+/*
+ * Set clock such that it would read <secs,nsecs> after 00:00:00 UTC,
+ * 1 January, 1970 if the current system time was <system_time>.
+ */
+#define XENPF_settime             17
+struct xenpf_settime {
+	/* IN variables. */
+	uint32_t secs;
+	uint32_t nsecs;
+	uint64_t system_time;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime_t);
+
+/*
+ * Request memory range (@mfn, @mfn+@nr_mfns-1) to have type @type.
+ * On x86, @type is an architecture-defined MTRR memory type.
+ * On success, returns the MTRR that was used (@reg) and a handle that can
+ * be passed to XENPF_DEL_MEMTYPE to accurately tear down the new setting.
+ * (x86-specific).
+ */
+#define XENPF_add_memtype         31
+struct xenpf_add_memtype {
+	/* IN variables. */
+	xen_pfn_t mfn;
+	uint64_t nr_mfns;
+	uint32_t type;
+	/* OUT variables. */
+	uint32_t handle;
+	uint32_t reg;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_add_memtype_t);
+
+/*
+ * Tear down an existing memory-range type. If @handle is remembered then it
+ * should be passed in to accurately tear down the correct setting (in case
+ * of overlapping memory regions with differing types). If it is not known
+ * then @handle should be set to zero. In all cases @reg must be set.
+ * (x86-specific).
+ */
+#define XENPF_del_memtype         32
+struct xenpf_del_memtype {
+	/* IN variables. */
+	uint32_t handle;
+	uint32_t reg;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_del_memtype_t);
+
+/* Read current type of an MTRR (x86-specific). */
+#define XENPF_read_memtype        33
+struct xenpf_read_memtype {
+	/* IN variables. */
+	uint32_t reg;
+	/* OUT variables. */
+	xen_pfn_t mfn;
+	uint64_t nr_mfns;
+	uint32_t type;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_read_memtype_t);
+
+#define XENPF_microcode_update    35
+struct xenpf_microcode_update {
+	/* IN variables. */
+	GUEST_HANDLE(void) data;          /* Pointer to microcode data */
+	uint32_t length;                  /* Length of microcode data. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_microcode_update_t);
+
+#define XENPF_platform_quirk      39
+#define QUIRK_NOIRQBALANCING      1 /* Do not restrict IO-APIC RTE targets */
+#define QUIRK_IOAPIC_BAD_REGSEL   2 /* IO-APIC REGSEL forgets its value    */
+#define QUIRK_IOAPIC_GOOD_REGSEL  3 /* IO-APIC REGSEL behaves properly     */
+struct xenpf_platform_quirk {
+	/* IN variables. */
+	uint32_t quirk_id;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_platform_quirk_t);
+
+#define XENPF_efi_runtime_call    49
+#define XEN_EFI_get_time                      1
+#define XEN_EFI_set_time                      2
+#define XEN_EFI_get_wakeup_time               3
+#define XEN_EFI_set_wakeup_time               4
+#define XEN_EFI_get_next_high_monotonic_count 5
+#define XEN_EFI_get_variable                  6
+#define XEN_EFI_set_variable                  7
+#define XEN_EFI_get_next_variable_name        8
+#define XEN_EFI_query_variable_info           9
+#define XEN_EFI_query_capsule_capabilities   10
+#define XEN_EFI_update_capsule               11
+
+struct xenpf_efi_runtime_call {
+	uint32_t function;
+	/*
+	 * This field is generally used for per sub-function flags (defined
+	 * below), except for the XEN_EFI_get_next_high_monotonic_count case,
+	 * where it holds the single returned value.
+	 */
+	uint32_t misc;
+	xen_ulong_t status;
+	union {
+#define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001
+		struct {
+			struct xenpf_efi_time {
+				uint16_t year;
+				uint8_t month;
+				uint8_t day;
+				uint8_t hour;
+				uint8_t min;
+				uint8_t sec;
+				uint32_t ns;
+				int16_t tz;
+				uint8_t daylight;
+			} time;
+			uint32_t resolution;
+			uint32_t accuracy;
+		} get_time;
+
+		struct xenpf_efi_time set_time;
+
+#define XEN_EFI_GET_WAKEUP_TIME_ENABLED 0x00000001
+#define XEN_EFI_GET_WAKEUP_TIME_PENDING 0x00000002
+		struct xenpf_efi_time get_wakeup_time;
+
+#define XEN_EFI_SET_WAKEUP_TIME_ENABLE      0x00000001
+#define XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY 0x00000002
+		struct xenpf_efi_time set_wakeup_time;
+
+#define XEN_EFI_VARIABLE_NON_VOLATILE       0x00000001
+#define XEN_EFI_VARIABLE_BOOTSERVICE_ACCESS 0x00000002
+#define XEN_EFI_VARIABLE_RUNTIME_ACCESS     0x00000004
+		struct {
+			GUEST_HANDLE(void) name;  /* UCS-2/UTF-16 string */
+			xen_ulong_t size;
+			GUEST_HANDLE(void) data;
+			struct xenpf_efi_guid {
+				uint32_t data1;
+				uint16_t data2;
+				uint16_t data3;
+				uint8_t data4[8];
+			} vendor_guid;
+		} get_variable, set_variable;
+
+		struct {
+			xen_ulong_t size;
+			GUEST_HANDLE(void) name;  /* UCS-2/UTF-16 string */
+			struct xenpf_efi_guid vendor_guid;
+		} get_next_variable_name;
+
+		struct {
+			uint32_t attr;
+			uint64_t max_store_size;
+			uint64_t remain_store_size;
+			uint64_t max_size;
+		} query_variable_info;
+
+		struct {
+			GUEST_HANDLE(void) capsule_header_array;
+			xen_ulong_t capsule_count;
+			uint64_t max_capsule_size;
+			uint32_t reset_type;
+		} query_capsule_capabilities;
+
+		struct {
+			GUEST_HANDLE(void) capsule_header_array;
+			xen_ulong_t capsule_count;
+			uint64_t sg_list; /* machine address */
+		} update_capsule;
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_efi_runtime_call);
+
+#define  XEN_FW_EFI_VERSION        0
+#define  XEN_FW_EFI_CONFIG_TABLE   1
+#define  XEN_FW_EFI_VENDOR         2
+#define  XEN_FW_EFI_MEM_INFO       3
+#define  XEN_FW_EFI_RT_VERSION     4
+
+#define XENPF_firmware_info       50
+#define XEN_FW_DISK_INFO          1 /* from int 13 AH=08/41/48 */
+#define XEN_FW_DISK_MBR_SIGNATURE 2 /* from MBR offset 0x1b8 */
+#define XEN_FW_VBEDDC_INFO        3 /* from int 10 AX=4f15 */
+#define XEN_FW_EFI_INFO           4 /* from EFI */
+#define XEN_FW_KBD_SHIFT_FLAGS    5 /* Int16, Fn02: Get keyboard shift flags. */
+
+struct xenpf_firmware_info {
+	/* IN variables. */
+	uint32_t type;
+	uint32_t index;
+	/* OUT variables. */
+	union {
+		struct {
+			/* Int13, Fn48: Check Extensions Present. */
+			uint8_t device;                   /* %dl: bios device number */
+			uint8_t version;                  /* %ah: major version      */
+			uint16_t interface_support;       /* %cx: support bitmap     */
+			/* Int13, Fn08: Legacy Get Device Parameters. */
+			uint16_t legacy_max_cylinder;     /* %cl[7:6]:%ch: max cyl # */
+			uint8_t legacy_max_head;          /* %dh: max head #         */
+			uint8_t legacy_sectors_per_track; /* %cl[5:0]: max sector #  */
+			/* Int13, Fn41: Get Device Parameters (as filled into %ds:%esi). */
+			/* NB. First uint16_t of buffer must be set to buffer size.      */
+			GUEST_HANDLE(void) edd_params;
+		} disk_info; /* XEN_FW_DISK_INFO */
+		struct {
+			uint8_t device;                   /* bios device number  */
+			uint32_t mbr_signature;           /* offset 0x1b8 in mbr */
+		} disk_mbr_signature; /* XEN_FW_DISK_MBR_SIGNATURE */
+		struct {
+			/* Int10, AX=4F15: Get EDID info. */
+			uint8_t capabilities;
+			uint8_t edid_transfer_time;
+			/* must refer to 128-byte buffer */
+			GUEST_HANDLE(uchar) edid;
+		} vbeddc_info; /* XEN_FW_VBEDDC_INFO */
+
+		union xenpf_efi_info {
+			uint32_t version;
+			struct {
+				uint64_t addr;   /* EFI_CONFIGURATION_TABLE */
+				uint32_t nent;
+			} cfg;
+			struct {
+				uint32_t revision;
+				uint32_t bufsz;  /* input, in bytes */
+				GUEST_HANDLE(void) name;
+				/* UCS-2/UTF-16 string */
+			} vendor;
+			struct {
+				uint64_t addr;
+				uint64_t size;
+				uint64_t attr;
+				uint32_t type;
+			} mem;
+		} efi_info; /* XEN_FW_EFI_INFO */
+
+		uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_firmware_info_t);
+
+#define XENPF_enter_acpi_sleep    51
+struct xenpf_enter_acpi_sleep {
+	/* IN variables */
+	uint16_t val_a;             /* PM1a control / sleep type A. */
+	uint16_t val_b;             /* PM1b control / sleep type B. */
+	uint32_t sleep_state;       /* Which state to enter (Sn). */
+#define XENPF_ACPI_SLEEP_EXTENDED 0x00000001
+	uint32_t flags;             /* XENPF_ACPI_SLEEP_*. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_enter_acpi_sleep_t);
+
+#define XENPF_change_freq         52
+struct xenpf_change_freq {
+	/* IN variables */
+	uint32_t flags; /* Must be zero. */
+	uint32_t cpu;   /* Physical cpu. */
+	uint64_t freq;  /* New frequency (Hz). */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_change_freq_t);
+
+/*
+ * Get idle times (nanoseconds since boot) for physical CPUs specified in the
+ * @cpumap_bitmap with range [0..@cpumap_nr_cpus-1]. The @idletime array is
+ * indexed by CPU number; only entries with the corresponding @cpumap_bitmap
+ * bit set are written to. On return, @cpumap_bitmap is modified so that any
+ * non-existent CPUs are cleared. Such CPUs have their @idletime array entry
+ * cleared.
+ */
+#define XENPF_getidletime         53
+struct xenpf_getidletime {
+	/* IN/OUT variables */
+	/* IN: CPUs to interrogate; OUT: subset of IN which are present */
+	GUEST_HANDLE(uchar) cpumap_bitmap;
+	/* IN variables */
+	/* Size of cpumap bitmap. */
+	uint32_t cpumap_nr_cpus;
+	/* Must be indexable for every cpu in cpumap_bitmap. */
+	GUEST_HANDLE(uint64_t) idletime;
+	/* OUT variables */
+	/* System time when the idletime snapshots were taken. */
+	uint64_t now;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_getidletime_t);
+
+#define XENPF_set_processor_pminfo      54
+
+/* ability bits */
+#define XEN_PROCESSOR_PM_CX	1
+#define XEN_PROCESSOR_PM_PX	2
+#define XEN_PROCESSOR_PM_TX	4
+
+/* cmd type */
+#define XEN_PM_CX   0
+#define XEN_PM_PX   1
+#define XEN_PM_TX   2
+#define XEN_PM_PDC  3
+/* Px sub info type */
+#define XEN_PX_PCT   1
+#define XEN_PX_PSS   2
+#define XEN_PX_PPC   4
+#define XEN_PX_PSD   8
+
+struct xen_power_register {
+	uint32_t     space_id;
+	uint32_t     bit_width;
+	uint32_t     bit_offset;
+	uint32_t     access_size;
+	uint64_t     address;
+};
+
+struct xen_processor_csd {
+	uint32_t    domain;      /* domain number of one dependent group */
+	uint32_t    coord_type;  /* coordination type */
+	uint32_t    num;         /* number of processors in same domain */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_processor_csd);
+
+struct xen_processor_cx {
+	struct xen_power_register  reg; /* GAS for Cx trigger register */
+	uint8_t     type;     /* cstate value, c0: 0, c1: 1, ... */
+	uint32_t    latency;  /* worst latency (ms) to enter/exit this cstate */
+	uint32_t    power;    /* average power consumption(mW) */
+	uint32_t    dpcnt;    /* number of dependency entries */
+	GUEST_HANDLE(xen_processor_csd) dp; /* NULL if no dependency */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_processor_cx);
+
+struct xen_processor_flags {
+	uint32_t bm_control:1;
+	uint32_t bm_check:1;
+	uint32_t has_cst:1;
+	uint32_t power_setup_done:1;
+	uint32_t bm_rld_set:1;
+};
+
+struct xen_processor_power {
+	uint32_t count;  /* number of C state entries in array below */
+	struct xen_processor_flags flags;  /* global flags of this processor */
+	GUEST_HANDLE(xen_processor_cx) states; /* supported c states */
+};
+
+struct xen_pct_register {
+	uint8_t  descriptor;
+	uint16_t length;
+	uint8_t  space_id;
+	uint8_t  bit_width;
+	uint8_t  bit_offset;
+	uint8_t  reserved;
+	uint64_t address;
+};
+
+struct xen_processor_px {
+	uint64_t core_frequency; /* megahertz */
+	uint64_t power;      /* milliWatts */
+	uint64_t transition_latency; /* microseconds */
+	uint64_t bus_master_latency; /* microseconds */
+	uint64_t control;        /* control value */
+	uint64_t status;     /* success indicator */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_processor_px);
+
+struct xen_psd_package {
+	uint64_t num_entries;
+	uint64_t revision;
+	uint64_t domain;
+	uint64_t coord_type;
+	uint64_t num_processors;
+};
+
+struct xen_processor_performance {
+	uint32_t flags;     /* flag for Px sub info type */
+	uint32_t platform_limit;  /* Platform limitation on freq usage */
+	struct xen_pct_register control_register;
+	struct xen_pct_register status_register;
+	uint32_t state_count;     /* total available performance states */
+	GUEST_HANDLE(xen_processor_px) states;
+	struct xen_psd_package domain_info;
+	uint32_t shared_type;     /* coordination type of this processor */
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_processor_performance);
+
+struct xenpf_set_processor_pminfo {
+	/* IN variables */
+	uint32_t id;    /* ACPI CPU ID */
+	uint32_t type;  /* {XEN_PM_CX, XEN_PM_PX} */
+	union {
+		struct xen_processor_power          power;/* Cx: _CST/_CSD */
+		struct xen_processor_performance    perf; /* Px: _PPC/_PCT/_PSS/_PSD */
+		GUEST_HANDLE(uint32_t)              pdc;
+	};
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_set_processor_pminfo);
+
+#define XENPF_get_cpuinfo 55
+struct xenpf_pcpuinfo {
+	/* IN */
+	uint32_t xen_cpuid;
+	/* OUT */
+	/* The maxium cpu_id that is present */
+	uint32_t max_present;
+#define XEN_PCPU_FLAGS_ONLINE   1
+	/* Correponding xen_cpuid is not present*/
+#define XEN_PCPU_FLAGS_INVALID  2
+	uint32_t flags;
+	uint32_t apic_id;
+	uint32_t acpi_id;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_pcpuinfo);
+
+#define XENPF_cpu_online	56
+#define XENPF_cpu_offline	57
+struct xenpf_cpu_ol {
+	uint32_t cpuid;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_cpu_ol);
+
+#define XENPF_cpu_hotadd	58
+struct xenpf_cpu_hotadd {
+	uint32_t apic_id;
+	uint32_t acpi_id;
+	uint32_t pxm;
+};
+
+#define XENPF_mem_hotadd	59
+struct xenpf_mem_hotadd {
+	uint64_t spfn;
+	uint64_t epfn;
+	uint32_t pxm;
+	uint32_t flags;
+};
+
+#define XENPF_core_parking     60
+struct xenpf_core_parking {
+	/* IN variables */
+#define XEN_CORE_PARKING_SET   1
+#define XEN_CORE_PARKING_GET   2
+	uint32_t type;
+	/* IN variables:  set cpu nums expected to be idled */
+	/* OUT variables: get cpu nums actually be idled */
+	uint32_t idle_nums;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_core_parking);
+
+struct xen_platform_op {
+	uint32_t cmd;
+	uint32_t interface_version; /* XENPF_INTERFACE_VERSION */
+	union {
+		struct xenpf_settime           settime;
+		struct xenpf_add_memtype       add_memtype;
+		struct xenpf_del_memtype       del_memtype;
+		struct xenpf_read_memtype      read_memtype;
+		struct xenpf_microcode_update  microcode;
+		struct xenpf_platform_quirk    platform_quirk;
+		struct xenpf_efi_runtime_call  efi_runtime_call;
+		struct xenpf_firmware_info     firmware_info;
+		struct xenpf_enter_acpi_sleep  enter_acpi_sleep;
+		struct xenpf_change_freq       change_freq;
+		struct xenpf_getidletime       getidletime;
+		struct xenpf_set_processor_pminfo set_pminfo;
+		struct xenpf_pcpuinfo          pcpu_info;
+		struct xenpf_cpu_ol            cpu_ol;
+		struct xenpf_cpu_hotadd        cpu_add;
+		struct xenpf_mem_hotadd        mem_add;
+		struct xenpf_core_parking      core_parking;
+		uint8_t                        pad[128];
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_platform_op_t);
+
+#endif /* __XEN_PUBLIC_PLATFORM_H__ */
diff --git a/kernel/include/xen/interface/sched.h b/kernel/include/xen/interface/sched.h
new file mode 100644
index 000000000..9ce083960
--- /dev/null
+++ b/kernel/include/xen/interface/sched.h
@@ -0,0 +1,111 @@
+/******************************************************************************
+ * sched.h
+ *
+ * Scheduler state interactions
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_SCHED_H__
+#define __XEN_PUBLIC_SCHED_H__
+
+#include <xen/interface/event_channel.h>
+
+/*
+ * The prototype for this hypercall is:
+ *  long sched_op_new(int cmd, void *arg)
+ * @cmd == SCHEDOP_??? (scheduler operation).
+ * @arg == Operation-specific extra argument(s), as described below.
+ *
+ * **NOTE**:
+ * Versions of Xen prior to 3.0.2 provide only the following legacy version
+ * of this hypercall, supporting only the commands yield, block and shutdown:
+ *  long sched_op(int cmd, unsigned long arg)
+ * @cmd == SCHEDOP_??? (scheduler operation).
+ * @arg == 0               (SCHEDOP_yield and SCHEDOP_block)
+ *      == SHUTDOWN_* code (SCHEDOP_shutdown)
+ */
+
+/*
+ * Voluntarily yield the CPU.
+ * @arg == NULL.
+ */
+#define SCHEDOP_yield       0
+
+/*
+ * Block execution of this VCPU until an event is received for processing.
+ * If called with event upcalls masked, this operation will atomically
+ * reenable event delivery and check for pending events before blocking the
+ * VCPU. This avoids a "wakeup waiting" race.
+ * @arg == NULL.
+ */
+#define SCHEDOP_block       1
+
+/*
+ * Halt execution of this domain (all VCPUs) and notify the system controller.
+ * @arg == pointer to sched_shutdown structure.
+ */
+#define SCHEDOP_shutdown    2
+struct sched_shutdown {
+    unsigned int reason; /* SHUTDOWN_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown);
+
+/*
+ * Poll a set of event-channel ports. Return when one or more are pending. An
+ * optional timeout may be specified.
+ * @arg == pointer to sched_poll structure.
+ */
+#define SCHEDOP_poll        3
+struct sched_poll {
+    GUEST_HANDLE(evtchn_port_t) ports;
+    unsigned int nr_ports;
+    uint64_t timeout;
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_poll);
+
+/*
+ * Declare a shutdown for another domain. The main use of this function is
+ * in interpreting shutdown requests and reasons for fully-virtualized
+ * domains.  A para-virtualized domain may use SCHEDOP_shutdown directly.
+ * @arg == pointer to sched_remote_shutdown structure.
+ */
+#define SCHEDOP_remote_shutdown        4
+struct sched_remote_shutdown {
+    domid_t domain_id;         /* Remote domain ID */
+    unsigned int reason;       /* SHUTDOWN_xxx reason */
+};
+
+/*
+ * Latch a shutdown code, so that when the domain later shuts down it
+ * reports this code to the control tools.
+ * @arg == as for SCHEDOP_shutdown.
+ */
+#define SCHEDOP_shutdown_code 5
+
+/*
+ * Setup, poke and destroy a domain watchdog timer.
+ * @arg == pointer to sched_watchdog structure.
+ * With id == 0, setup a domain watchdog timer to cause domain shutdown
+ *               after timeout, returns watchdog id.
+ * With id != 0 and timeout == 0, destroy domain watchdog timer.
+ * With id != 0 and timeout != 0, poke watchdog timer and set new timeout.
+ */
+#define SCHEDOP_watchdog    6
+struct sched_watchdog {
+    uint32_t id;                /* watchdog ID */
+    uint32_t timeout;           /* timeout */
+};
+
+/*
+ * Reason codes for SCHEDOP_shutdown. These may be interpreted by control
+ * software to determine the appropriate action. For the most part, Xen does
+ * not care about the shutdown code.
+ */
+#define SHUTDOWN_poweroff   0  /* Domain exited normally. Clean up and kill. */
+#define SHUTDOWN_reboot     1  /* Clean up, kill, and then restart.          */
+#define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
+#define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
+#define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
+
+#endif /* __XEN_PUBLIC_SCHED_H__ */
diff --git a/kernel/include/xen/interface/vcpu.h b/kernel/include/xen/interface/vcpu.h
new file mode 100644
index 000000000..b05288ce3
--- /dev/null
+++ b/kernel/include/xen/interface/vcpu.h
@@ -0,0 +1,175 @@
+/******************************************************************************
+ * vcpu.h
+ *
+ * VCPU initialisation, query, and hotplug.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_VCPU_H__
+#define __XEN_PUBLIC_VCPU_H__
+
+/*
+ * Prototype for this hypercall is:
+ *	int vcpu_op(int cmd, int vcpuid, void *extra_args)
+ * @cmd		   == VCPUOP_??? (VCPU operation).
+ * @vcpuid	   == VCPU to operate on.
+ * @extra_args == Operation-specific extra arguments (NULL if none).
+ */
+
+/*
+ * Initialise a VCPU. Each VCPU can be initialised only once. A
+ * newly-initialised VCPU will not run until it is brought up by VCPUOP_up.
+ *
+ * @extra_arg == pointer to vcpu_guest_context structure containing initial
+ *				 state for the VCPU.
+ */
+#define VCPUOP_initialise			 0
+
+/*
+ * Bring up a VCPU. This makes the VCPU runnable. This operation will fail
+ * if the VCPU has not been initialised (VCPUOP_initialise).
+ */
+#define VCPUOP_up					 1
+
+/*
+ * Bring down a VCPU (i.e., make it non-runnable).
+ * There are a few caveats that callers should observe:
+ *	1. This operation may return, and VCPU_is_up may return false, before the
+ *	   VCPU stops running (i.e., the command is asynchronous). It is a good
+ *	   idea to ensure that the VCPU has entered a non-critical loop before
+ *	   bringing it down. Alternatively, this operation is guaranteed
+ *	   synchronous if invoked by the VCPU itself.
+ *	2. After a VCPU is initialised, there is currently no way to drop all its
+ *	   references to domain memory. Even a VCPU that is down still holds
+ *	   memory references via its pagetable base pointer and GDT. It is good
+ *	   practise to move a VCPU onto an 'idle' or default page table, LDT and
+ *	   GDT before bringing it down.
+ */
+#define VCPUOP_down					 2
+
+/* Returns 1 if the given VCPU is up. */
+#define VCPUOP_is_up				 3
+
+/*
+ * Return information about the state and running time of a VCPU.
+ * @extra_arg == pointer to vcpu_runstate_info structure.
+ */
+#define VCPUOP_get_runstate_info	 4
+struct vcpu_runstate_info {
+		/* VCPU's current state (RUNSTATE_*). */
+		int		 state;
+		/* When was current state entered (system time, ns)? */
+		uint64_t state_entry_time;
+		/*
+		 * Time spent in each RUNSTATE_* (ns). The sum of these times is
+		 * guaranteed not to drift from system time.
+		 */
+		uint64_t time[4];
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_runstate_info);
+
+/* VCPU is currently running on a physical CPU. */
+#define RUNSTATE_running  0
+
+/* VCPU is runnable, but not currently scheduled on any physical CPU. */
+#define RUNSTATE_runnable 1
+
+/* VCPU is blocked (a.k.a. idle). It is therefore not runnable. */
+#define RUNSTATE_blocked  2
+
+/*
+ * VCPU is not runnable, but it is not blocked.
+ * This is a 'catch all' state for things like hotplug and pauses by the
+ * system administrator (or for critical sections in the hypervisor).
+ * RUNSTATE_blocked dominates this state (it is the preferred state).
+ */
+#define RUNSTATE_offline  3
+
+/*
+ * Register a shared memory area from which the guest may obtain its own
+ * runstate information without needing to execute a hypercall.
+ * Notes:
+ *	1. The registered address may be virtual or physical, depending on the
+ *	   platform. The virtual address should be registered on x86 systems.
+ *	2. Only one shared area may be registered per VCPU. The shared area is
+ *	   updated by the hypervisor each time the VCPU is scheduled. Thus
+ *	   runstate.state will always be RUNSTATE_running and
+ *	   runstate.state_entry_time will indicate the system time at which the
+ *	   VCPU was last scheduled to run.
+ * @extra_arg == pointer to vcpu_register_runstate_memory_area structure.
+ */
+#define VCPUOP_register_runstate_memory_area 5
+struct vcpu_register_runstate_memory_area {
+		union {
+				GUEST_HANDLE(vcpu_runstate_info) h;
+				struct vcpu_runstate_info *v;
+				uint64_t p;
+		} addr;
+};
+
+/*
+ * Set or stop a VCPU's periodic timer. Every VCPU has one periodic timer
+ * which can be set via these commands. Periods smaller than one millisecond
+ * may not be supported.
+ */
+#define VCPUOP_set_periodic_timer	 6 /* arg == vcpu_set_periodic_timer_t */
+#define VCPUOP_stop_periodic_timer	 7 /* arg == NULL */
+struct vcpu_set_periodic_timer {
+		uint64_t period_ns;
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_set_periodic_timer);
+
+/*
+ * Set or stop a VCPU's single-shot timer. Every VCPU has one single-shot
+ * timer which can be set via these commands.
+ */
+#define VCPUOP_set_singleshot_timer	 8 /* arg == vcpu_set_singleshot_timer_t */
+#define VCPUOP_stop_singleshot_timer 9 /* arg == NULL */
+struct vcpu_set_singleshot_timer {
+		uint64_t timeout_abs_ns;
+		uint32_t flags;			   /* VCPU_SSHOTTMR_??? */
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_set_singleshot_timer);
+
+/* Flags to VCPUOP_set_singleshot_timer. */
+ /* Require the timeout to be in the future (return -ETIME if it's passed). */
+#define _VCPU_SSHOTTMR_future (0)
+#define VCPU_SSHOTTMR_future  (1U << _VCPU_SSHOTTMR_future)
+
+/*
+ * Register a memory location in the guest address space for the
+ * vcpu_info structure.  This allows the guest to place the vcpu_info
+ * structure in a convenient place, such as in a per-cpu data area.
+ * The pointer need not be page aligned, but the structure must not
+ * cross a page boundary.
+ */
+#define VCPUOP_register_vcpu_info   10  /* arg == struct vcpu_info */
+struct vcpu_register_vcpu_info {
+    uint64_t mfn;    /* mfn of page to place vcpu_info */
+    uint32_t offset; /* offset within page */
+    uint32_t rsvd;   /* unused */
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_vcpu_info);
+
+/* Send an NMI to the specified VCPU. @extra_arg == NULL. */
+#define VCPUOP_send_nmi             11
+#endif /* __XEN_PUBLIC_VCPU_H__ */
diff --git a/kernel/include/xen/interface/version.h b/kernel/include/xen/interface/version.h
new file mode 100644
index 000000000..7ff649867
--- /dev/null
+++ b/kernel/include/xen/interface/version.h
@@ -0,0 +1,66 @@
+/******************************************************************************
+ * version.h
+ *
+ * Xen version, type, and compile information.
+ *
+ * Copyright (c) 2005, Nguyen Anh Quynh <aquynh@gmail.com>
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_VERSION_H__
+#define __XEN_PUBLIC_VERSION_H__
+
+/* NB. All ops return zero on success, except XENVER_version. */
+
+/* arg == NULL; returns major:minor (16:16). */
+#define XENVER_version      0
+
+/* arg == xen_extraversion_t. */
+#define XENVER_extraversion 1
+struct xen_extraversion {
+    char extraversion[16];
+};
+#define XEN_EXTRAVERSION_LEN (sizeof(struct xen_extraversion))
+
+/* arg == xen_compile_info_t. */
+#define XENVER_compile_info 2
+struct xen_compile_info {
+    char compiler[64];
+    char compile_by[16];
+    char compile_domain[32];
+    char compile_date[32];
+};
+
+#define XENVER_capabilities 3
+struct xen_capabilities_info {
+    char info[1024];
+};
+#define XEN_CAPABILITIES_INFO_LEN (sizeof(struct xen_capabilities_info))
+
+#define XENVER_changeset 4
+struct xen_changeset_info {
+    char info[64];
+};
+#define XEN_CHANGESET_INFO_LEN (sizeof(struct xen_changeset_info))
+
+#define XENVER_platform_parameters 5
+struct xen_platform_parameters {
+    xen_ulong_t virt_start;
+};
+
+#define XENVER_get_features 6
+struct xen_feature_info {
+    unsigned int submap_idx;    /* IN: which 32-bit submap to return */
+    uint32_t     submap;        /* OUT: 32-bit submap */
+};
+
+/* Declares the features reported by XENVER_get_features. */
+#include <xen/interface/features.h>
+
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
+/* arg == xen_domain_handle_t. */
+#define XENVER_guest_handle 8
+
+#endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/kernel/include/xen/interface/xen-mca.h b/kernel/include/xen/interface/xen-mca.h
new file mode 100644
index 000000000..73a4ea714
--- /dev/null
+++ b/kernel/include/xen/interface/xen-mca.h
@@ -0,0 +1,385 @@
+/******************************************************************************
+ * arch-x86/mca.h
+ * Guest OS machine check interface to x86 Xen.
+ *
+ * Contributed by Advanced Micro Devices, Inc.
+ * Author: Christoph Egger <Christoph.Egger@amd.com>
+ *
+ * Updated by Intel Corporation
+ * Author: Liu, Jinsong <jinsong.liu@intel.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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 __XEN_PUBLIC_ARCH_X86_MCA_H__
+#define __XEN_PUBLIC_ARCH_X86_MCA_H__
+
+/* Hypercall */
+#define __HYPERVISOR_mca __HYPERVISOR_arch_0
+
+#define XEN_MCA_INTERFACE_VERSION	0x01ecc003
+
+/* IN: Dom0 calls hypercall to retrieve nonurgent error log entry */
+#define XEN_MC_NONURGENT	0x1
+/* IN: Dom0 calls hypercall to retrieve urgent error log entry */
+#define XEN_MC_URGENT		0x2
+/* IN: Dom0 acknowledges previosly-fetched error log entry */
+#define XEN_MC_ACK		0x4
+
+/* OUT: All is ok */
+#define XEN_MC_OK		0x0
+/* OUT: Domain could not fetch data. */
+#define XEN_MC_FETCHFAILED	0x1
+/* OUT: There was no machine check data to fetch. */
+#define XEN_MC_NODATA		0x2
+
+#ifndef __ASSEMBLY__
+/* vIRQ injected to Dom0 */
+#define VIRQ_MCA VIRQ_ARCH_0
+
+/*
+ * mc_info entry types
+ * mca machine check info are recorded in mc_info entries.
+ * when fetch mca info, it can use MC_TYPE_... to distinguish
+ * different mca info.
+ */
+#define MC_TYPE_GLOBAL		0
+#define MC_TYPE_BANK		1
+#define MC_TYPE_EXTENDED	2
+#define MC_TYPE_RECOVERY	3
+
+struct mcinfo_common {
+	uint16_t type; /* structure type */
+	uint16_t size; /* size of this struct in bytes */
+};
+
+#define MC_FLAG_CORRECTABLE	(1 << 0)
+#define MC_FLAG_UNCORRECTABLE	(1 << 1)
+#define MC_FLAG_RECOVERABLE	(1 << 2)
+#define MC_FLAG_POLLED		(1 << 3)
+#define MC_FLAG_RESET		(1 << 4)
+#define MC_FLAG_CMCI		(1 << 5)
+#define MC_FLAG_MCE		(1 << 6)
+
+/* contains x86 global mc information */
+struct mcinfo_global {
+	struct mcinfo_common common;
+
+	uint16_t mc_domid; /* running domain at the time in error */
+	uint16_t mc_vcpuid; /* virtual cpu scheduled for mc_domid */
+	uint32_t mc_socketid; /* physical socket of the physical core */
+	uint16_t mc_coreid; /* physical impacted core */
+	uint16_t mc_core_threadid; /* core thread of physical core */
+	uint32_t mc_apicid;
+	uint32_t mc_flags;
+	uint64_t mc_gstatus; /* global status */
+};
+
+/* contains x86 bank mc information */
+struct mcinfo_bank {
+	struct mcinfo_common common;
+
+	uint16_t mc_bank; /* bank nr */
+	uint16_t mc_domid; /* domain referenced by mc_addr if valid */
+	uint64_t mc_status; /* bank status */
+	uint64_t mc_addr; /* bank address */
+	uint64_t mc_misc;
+	uint64_t mc_ctrl2;
+	uint64_t mc_tsc;
+};
+
+struct mcinfo_msr {
+	uint64_t reg; /* MSR */
+	uint64_t value; /* MSR value */
+};
+
+/* contains mc information from other or additional mc MSRs */
+struct mcinfo_extended {
+	struct mcinfo_common common;
+	uint32_t mc_msrs; /* Number of msr with valid values. */
+	/*
+	 * Currently Intel extended MSR (32/64) include all gp registers
+	 * and E(R)FLAGS, E(R)IP, E(R)MISC, up to 11/19 of them might be
+	 * useful at present. So expand this array to 16/32 to leave room.
+	 */
+	struct mcinfo_msr mc_msr[sizeof(void *) * 4];
+};
+
+/* Recovery Action flags. Giving recovery result information to DOM0 */
+
+/* Xen takes successful recovery action, the error is recovered */
+#define REC_ACTION_RECOVERED (0x1 << 0)
+/* No action is performed by XEN */
+#define REC_ACTION_NONE (0x1 << 1)
+/* It's possible DOM0 might take action ownership in some case */
+#define REC_ACTION_NEED_RESET (0x1 << 2)
+
+/*
+ * Different Recovery Action types, if the action is performed successfully,
+ * REC_ACTION_RECOVERED flag will be returned.
+ */
+
+/* Page Offline Action */
+#define MC_ACTION_PAGE_OFFLINE (0x1 << 0)
+/* CPU offline Action */
+#define MC_ACTION_CPU_OFFLINE (0x1 << 1)
+/* L3 cache disable Action */
+#define MC_ACTION_CACHE_SHRINK (0x1 << 2)
+
+/*
+ * Below interface used between XEN/DOM0 for passing XEN's recovery action
+ * information to DOM0.
+ */
+struct page_offline_action {
+	/* Params for passing the offlined page number to DOM0 */
+	uint64_t mfn;
+	uint64_t status;
+};
+
+struct cpu_offline_action {
+	/* Params for passing the identity of the offlined CPU to DOM0 */
+	uint32_t mc_socketid;
+	uint16_t mc_coreid;
+	uint16_t mc_core_threadid;
+};
+
+#define MAX_UNION_SIZE 16
+struct mcinfo_recovery {
+	struct mcinfo_common common;
+	uint16_t mc_bank; /* bank nr */
+	uint8_t action_flags;
+	uint8_t action_types;
+	union {
+		struct page_offline_action page_retire;
+		struct cpu_offline_action cpu_offline;
+		uint8_t pad[MAX_UNION_SIZE];
+	} action_info;
+};
+
+
+#define MCINFO_MAXSIZE 768
+struct mc_info {
+	/* Number of mcinfo_* entries in mi_data */
+	uint32_t mi_nentries;
+	uint32_t flags;
+	uint64_t mi_data[(MCINFO_MAXSIZE - 1) / 8];
+};
+DEFINE_GUEST_HANDLE_STRUCT(mc_info);
+
+#define __MC_MSR_ARRAYSIZE 8
+#define __MC_MSR_MCGCAP 0
+#define __MC_NMSRS 1
+#define MC_NCAPS 7
+struct mcinfo_logical_cpu {
+	uint32_t mc_cpunr;
+	uint32_t mc_chipid;
+	uint16_t mc_coreid;
+	uint16_t mc_threadid;
+	uint32_t mc_apicid;
+	uint32_t mc_clusterid;
+	uint32_t mc_ncores;
+	uint32_t mc_ncores_active;
+	uint32_t mc_nthreads;
+	uint32_t mc_cpuid_level;
+	uint32_t mc_family;
+	uint32_t mc_vendor;
+	uint32_t mc_model;
+	uint32_t mc_step;
+	char mc_vendorid[16];
+	char mc_brandid[64];
+	uint32_t mc_cpu_caps[MC_NCAPS];
+	uint32_t mc_cache_size;
+	uint32_t mc_cache_alignment;
+	uint32_t mc_nmsrvals;
+	struct mcinfo_msr mc_msrvalues[__MC_MSR_ARRAYSIZE];
+};
+DEFINE_GUEST_HANDLE_STRUCT(mcinfo_logical_cpu);
+
+/*
+ * Prototype:
+ *    uint32_t x86_mcinfo_nentries(struct mc_info *mi);
+ */
+#define x86_mcinfo_nentries(_mi)    \
+	((_mi)->mi_nentries)
+/*
+ * Prototype:
+ *    struct mcinfo_common *x86_mcinfo_first(struct mc_info *mi);
+ */
+#define x86_mcinfo_first(_mi)       \
+	((struct mcinfo_common *)(_mi)->mi_data)
+/*
+ * Prototype:
+ *    struct mcinfo_common *x86_mcinfo_next(struct mcinfo_common *mic);
+ */
+#define x86_mcinfo_next(_mic)       \
+	((struct mcinfo_common *)((uint8_t *)(_mic) + (_mic)->size))
+
+/*
+ * Prototype:
+ *    void x86_mcinfo_lookup(void *ret, struct mc_info *mi, uint16_t type);
+ */
+static inline void x86_mcinfo_lookup(struct mcinfo_common **ret,
+				     struct mc_info *mi, uint16_t type)
+{
+	uint32_t i;
+	struct mcinfo_common *mic;
+	bool found = 0;
+
+	if (!ret || !mi)
+		return;
+
+	mic = x86_mcinfo_first(mi);
+	for (i = 0; i < x86_mcinfo_nentries(mi); i++) {
+		if (mic->type == type) {
+			found = 1;
+			break;
+		}
+		mic = x86_mcinfo_next(mic);
+	}
+
+	*ret = found ? mic : NULL;
+}
+
+/*
+ * Fetch machine check data from hypervisor.
+ */
+#define XEN_MC_fetch		1
+struct xen_mc_fetch {
+	/*
+	 * IN: XEN_MC_NONURGENT, XEN_MC_URGENT,
+	 * XEN_MC_ACK if ack'king an earlier fetch
+	 * OUT: XEN_MC_OK, XEN_MC_FETCHAILED, XEN_MC_NODATA
+	 */
+	uint32_t flags;
+	uint32_t _pad0;
+	/* OUT: id for ack, IN: id we are ack'ing */
+	uint64_t fetch_id;
+
+	/* OUT variables. */
+	GUEST_HANDLE(mc_info) data;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc_fetch);
+
+
+/*
+ * This tells the hypervisor to notify a DomU about the machine check error
+ */
+#define XEN_MC_notifydomain	2
+struct xen_mc_notifydomain {
+	/* IN variables */
+	uint16_t mc_domid; /* The unprivileged domain to notify */
+	uint16_t mc_vcpuid; /* The vcpu in mc_domid to notify */
+
+	/* IN/OUT variables */
+	uint32_t flags;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc_notifydomain);
+
+#define XEN_MC_physcpuinfo	3
+struct xen_mc_physcpuinfo {
+	/* IN/OUT */
+	uint32_t ncpus;
+	uint32_t _pad0;
+	/* OUT */
+	GUEST_HANDLE(mcinfo_logical_cpu) info;
+};
+
+#define XEN_MC_msrinject	4
+#define MC_MSRINJ_MAXMSRS	8
+struct xen_mc_msrinject {
+	/* IN */
+	uint32_t mcinj_cpunr; /* target processor id */
+	uint32_t mcinj_flags; /* see MC_MSRINJ_F_* below */
+	uint32_t mcinj_count; /* 0 .. count-1 in array are valid */
+	uint32_t _pad0;
+	struct mcinfo_msr mcinj_msr[MC_MSRINJ_MAXMSRS];
+};
+
+/* Flags for mcinj_flags above; bits 16-31 are reserved */
+#define MC_MSRINJ_F_INTERPOSE	0x1
+
+#define XEN_MC_mceinject	5
+struct xen_mc_mceinject {
+	unsigned int mceinj_cpunr; /* target processor id */
+};
+
+struct xen_mc {
+	uint32_t cmd;
+	uint32_t interface_version; /* XEN_MCA_INTERFACE_VERSION */
+	union {
+		struct xen_mc_fetch        mc_fetch;
+		struct xen_mc_notifydomain mc_notifydomain;
+		struct xen_mc_physcpuinfo  mc_physcpuinfo;
+		struct xen_mc_msrinject    mc_msrinject;
+		struct xen_mc_mceinject    mc_mceinject;
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc);
+
+/* Fields are zero when not available */
+struct xen_mce {
+	__u64 status;
+	__u64 misc;
+	__u64 addr;
+	__u64 mcgstatus;
+	__u64 ip;
+	__u64 tsc;	/* cpu time stamp counter */
+	__u64 time;	/* wall time_t when error was detected */
+	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
+	__u8  inject_flags;	/* software inject flags */
+	__u16  pad;
+	__u32 cpuid;	/* CPUID 1 EAX */
+	__u8  cs;		/* code segment */
+	__u8  bank;	/* machine check bank */
+	__u8  cpu;	/* cpu number; obsolete; use extcpu now */
+	__u8  finished;   /* entry is valid */
+	__u32 extcpu;	/* linux cpu number that detected the error */
+	__u32 socketid;	/* CPU socket ID */
+	__u32 apicid;	/* CPU initial apic ID */
+	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
+};
+
+/*
+ * This structure contains all data related to the MCE log.  Also
+ * carries a signature to make it easier to find from external
+ * debugging tools.  Each entry is only valid when its finished flag
+ * is set.
+ */
+
+#define XEN_MCE_LOG_LEN 32
+
+struct xen_mce_log {
+	char signature[12]; /* "MACHINECHECK" */
+	unsigned len;	    /* = XEN_MCE_LOG_LEN */
+	unsigned next;
+	unsigned flags;
+	unsigned recordlen;	/* length of struct xen_mce */
+	struct xen_mce entry[XEN_MCE_LOG_LEN];
+};
+
+#define XEN_MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
+
+#define XEN_MCE_LOG_SIGNATURE	"MACHINECHECK"
+
+#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
+#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
+#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
+
+#endif /* __ASSEMBLY__ */
+#endif /* __XEN_PUBLIC_ARCH_X86_MCA_H__ */
diff --git a/kernel/include/xen/interface/xen.h b/kernel/include/xen/interface/xen.h
new file mode 100644
index 000000000..a48378958
--- /dev/null
+++ b/kernel/include/xen/interface/xen.h
@@ -0,0 +1,758 @@
+/******************************************************************************
+ * xen.h
+ *
+ * Guest OS interface to Xen.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __XEN_PUBLIC_XEN_H__
+#define __XEN_PUBLIC_XEN_H__
+
+#include <asm/xen/interface.h>
+
+/*
+ * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
+ */
+
+/*
+ * x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5.
+ *         EAX = return value
+ *         (argument registers may be clobbered on return)
+ * x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6.
+ *         RAX = return value
+ *         (argument registers not clobbered on return; RCX, R11 are)
+ */
+#define __HYPERVISOR_set_trap_table        0
+#define __HYPERVISOR_mmu_update            1
+#define __HYPERVISOR_set_gdt               2
+#define __HYPERVISOR_stack_switch          3
+#define __HYPERVISOR_set_callbacks         4
+#define __HYPERVISOR_fpu_taskswitch        5
+#define __HYPERVISOR_sched_op_compat       6
+#define __HYPERVISOR_dom0_op               7
+#define __HYPERVISOR_set_debugreg          8
+#define __HYPERVISOR_get_debugreg          9
+#define __HYPERVISOR_update_descriptor    10
+#define __HYPERVISOR_memory_op            12
+#define __HYPERVISOR_multicall            13
+#define __HYPERVISOR_update_va_mapping    14
+#define __HYPERVISOR_set_timer_op         15
+#define __HYPERVISOR_event_channel_op_compat 16
+#define __HYPERVISOR_xen_version          17
+#define __HYPERVISOR_console_io           18
+#define __HYPERVISOR_physdev_op_compat    19
+#define __HYPERVISOR_grant_table_op       20
+#define __HYPERVISOR_vm_assist            21
+#define __HYPERVISOR_update_va_mapping_otherdomain 22
+#define __HYPERVISOR_iret                 23 /* x86 only */
+#define __HYPERVISOR_vcpu_op              24
+#define __HYPERVISOR_set_segment_base     25 /* x86/64 only */
+#define __HYPERVISOR_mmuext_op            26
+#define __HYPERVISOR_xsm_op               27
+#define __HYPERVISOR_nmi_op               28
+#define __HYPERVISOR_sched_op             29
+#define __HYPERVISOR_callback_op          30
+#define __HYPERVISOR_xenoprof_op          31
+#define __HYPERVISOR_event_channel_op     32
+#define __HYPERVISOR_physdev_op           33
+#define __HYPERVISOR_hvm_op               34
+#define __HYPERVISOR_sysctl               35
+#define __HYPERVISOR_domctl               36
+#define __HYPERVISOR_kexec_op             37
+#define __HYPERVISOR_tmem_op              38
+#define __HYPERVISOR_xc_reserved_op       39 /* reserved for XenClient */
+
+/* Architecture-specific hypercall definitions. */
+#define __HYPERVISOR_arch_0               48
+#define __HYPERVISOR_arch_1               49
+#define __HYPERVISOR_arch_2               50
+#define __HYPERVISOR_arch_3               51
+#define __HYPERVISOR_arch_4               52
+#define __HYPERVISOR_arch_5               53
+#define __HYPERVISOR_arch_6               54
+#define __HYPERVISOR_arch_7               55
+
+/*
+ * VIRTUAL INTERRUPTS
+ *
+ * Virtual interrupts that a guest OS may receive from Xen.
+ * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
+ * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
+ * The latter can be allocated only once per guest: they must initially be
+ * allocated to VCPU0 but can subsequently be re-bound.
+ */
+#define VIRQ_TIMER      0  /* V. Timebase update, and/or requested timeout.  */
+#define VIRQ_DEBUG      1  /* V. Request guest to dump debug info.           */
+#define VIRQ_CONSOLE    2  /* G. (DOM0) Bytes received on emergency console. */
+#define VIRQ_DOM_EXC    3  /* G. (DOM0) Exceptional event for some domain.   */
+#define VIRQ_TBUF       4  /* G. (DOM0) Trace buffer has records available.  */
+#define VIRQ_DEBUGGER   6  /* G. (DOM0) A domain has paused for debugging.   */
+#define VIRQ_XENOPROF   7  /* V. XenOprofile interrupt: new sample available */
+#define VIRQ_CON_RING   8  /* G. (DOM0) Bytes received on console            */
+#define VIRQ_PCPU_STATE 9  /* G. (DOM0) PCPU state changed                   */
+#define VIRQ_MEM_EVENT  10 /* G. (DOM0) A memory event has occured           */
+#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient                     */
+#define VIRQ_ENOMEM     12 /* G. (DOM0) Low on heap memory       */
+
+/* Architecture-specific VIRQ definitions. */
+#define VIRQ_ARCH_0    16
+#define VIRQ_ARCH_1    17
+#define VIRQ_ARCH_2    18
+#define VIRQ_ARCH_3    19
+#define VIRQ_ARCH_4    20
+#define VIRQ_ARCH_5    21
+#define VIRQ_ARCH_6    22
+#define VIRQ_ARCH_7    23
+
+#define NR_VIRQS       24
+
+/*
+ * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
+ *                                         unsigned count, unsigned *done_out,
+ *                                         unsigned foreigndom)
+ * @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
+ * @count is the length of the above array.
+ * @pdone is an output parameter indicating number of completed operations
+ * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
+ *                    hypercall invocation. Can be DOMID_SELF.
+ * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
+ *                     in this hypercall invocation. The value of this field
+ *                     (x) encodes the PFD as follows:
+ *                     x == 0 => PFD == DOMID_SELF
+ *                     x != 0 => PFD == x - 1
+ *
+ * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
+ * -------------
+ * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
+ * Updates an entry in a page table belonging to PFD. If updating an L1 table,
+ * and the new table entry is valid/present, the mapped frame must belong to
+ * FD. If attempting to map an I/O page then the caller assumes the privilege
+ * of the FD.
+ * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
+ * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
+ * ptr[:2]  -- Machine address of the page-table entry to modify.
+ * val      -- Value to write.
+ *
+ * There also certain implicit requirements when using this hypercall. The
+ * pages that make up a pagetable must be mapped read-only in the guest.
+ * This prevents uncontrolled guest updates to the pagetable. Xen strictly
+ * enforces this, and will disallow any pagetable update which will end up
+ * mapping pagetable page RW, and will disallow using any writable page as a
+ * pagetable. In practice it means that when constructing a page table for a
+ * process, thread, etc, we MUST be very dilligient in following these rules:
+ *  1). Start with top-level page (PGD or in Xen language: L4). Fill out
+ *      the entries.
+ *  2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
+ *      or L2).
+ *  3). Start filling out the PTE table (L1) with the PTE entries. Once
+ *      done, make sure to set each of those entries to RO (so writeable bit
+ *      is unset). Once that has been completed, set the PMD (L2) for this
+ *      PTE table as RO.
+ *  4). When completed with all of the PMD (L2) entries, and all of them have
+ *      been set to RO, make sure to set RO the PUD (L3). Do the same
+ *      operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
+ *  5). Now before you can use those pages (so setting the cr3), you MUST also
+ *      pin them so that the hypervisor can verify the entries. This is done
+ *      via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
+ *      number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
+ *      MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
+ *      issued.
+ * For 32-bit guests, the L4 is not used (as there is less pagetables), so
+ * instead use L3.
+ * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
+ * hypercall. Also if so desired the OS can also try to write to the PTE
+ * and be trapped by the hypervisor (as the PTE entry is RO).
+ *
+ * To deallocate the pages, the operations are the reverse of the steps
+ * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
+ * pagetable MUST not be in use (meaning that the cr3 is not set to it).
+ *
+ * ptr[1:0] == MMU_MACHPHYS_UPDATE:
+ * Updates an entry in the machine->pseudo-physical mapping table.
+ * ptr[:2]  -- Machine address within the frame whose mapping to modify.
+ *             The frame must belong to the FD, if one is specified.
+ * val      -- Value to write into the mapping entry.
+ *
+ * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
+ * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
+ * with those in @val.
+ *
+ * @val is usually the machine frame number along with some attributes.
+ * The attributes by default follow the architecture defined bits. Meaning that
+ * if this is a X86_64 machine and four page table layout is used, the layout
+ * of val is:
+ *  - 63 if set means No execute (NX)
+ *  - 46-13 the machine frame number
+ *  - 12 available for guest
+ *  - 11 available for guest
+ *  - 10 available for guest
+ *  - 9 available for guest
+ *  - 8 global
+ *  - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
+ *  - 6 dirty
+ *  - 5 accessed
+ *  - 4 page cached disabled
+ *  - 3 page write through
+ *  - 2 userspace accessible
+ *  - 1 writeable
+ *  - 0 present
+ *
+ *  The one bits that does not fit with the default layout is the PAGE_PSE
+ *  also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
+ *  HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
+ *  (or 2MB) instead of using the PAGE_PSE bit.
+ *
+ *  The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
+ *  using it as the Page Attribute Table (PAT) bit - for details on it please
+ *  refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
+ *  pages instead of using MTRRs.
+ *
+ *  The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
+ *                    PAT4                 PAT0
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WC | WB | UC | UC- | WC | WB |  <= Linux
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WT | WB | UC | UC- | WT | WB |  <= BIOS (default when machine boots)
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | rsv | rsv | WP | WC | UC | UC- | WT | WB |  <= Xen
+ *  +-----+-----+----+----+----+-----+----+----+
+ *
+ *  The lookup of this index table translates to looking up
+ *  Bit 7, Bit 4, and Bit 3 of val entry:
+ *
+ *  PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
+ *
+ *  If all bits are off, then we are using PAT0. If bit 3 turned on,
+ *  then we are using PAT1, if bit 3 and bit 4, then PAT2..
+ *
+ *  As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
+ *  that if a guest that follows Linux's PAT setup and would like to set Write
+ *  Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
+ *  set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
+ *  caching as:
+ *
+ *   WB = none (so PAT0)
+ *   WC = PWT (bit 3 on)
+ *   UC = PWT | PCD (bit 3 and 4 are on).
+ *
+ * To make it work with Xen, it needs to translate the WC bit as so:
+ *
+ *  PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
+ *
+ * And to translate back it would:
+ *
+ * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
+ */
+#define MMU_NORMAL_PT_UPDATE      0 /* checked '*ptr = val'. ptr is MA.       */
+#define MMU_MACHPHYS_UPDATE       1 /* ptr = MA of frame to modify entry for  */
+#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
+
+/*
+ * MMU EXTENDED OPERATIONS
+ *
+ * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
+ *                                        unsigned int count,
+ *                                        unsigned int *pdone,
+ *                                        unsigned int foreigndom)
+ */
+/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
+ * A foreigndom (FD) can be specified (or DOMID_SELF for none).
+ * Where the FD has some effect, it is described below.
+ *
+ * cmd: MMUEXT_(UN)PIN_*_TABLE
+ * mfn: Machine frame number to be (un)pinned as a p.t. page.
+ *      The frame must belong to the FD, if one is specified.
+ *
+ * cmd: MMUEXT_NEW_BASEPTR
+ * mfn: Machine frame number of new page-table base to install in MMU.
+ *
+ * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only]
+ * mfn: Machine frame number of new page-table base to install in MMU
+ *      when in user space.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_LOCAL
+ * No additional arguments. Flushes local TLB.
+ *
+ * cmd: MMUEXT_INVLPG_LOCAL
+ * linear_addr: Linear address to be flushed from the local TLB.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_MULTI
+ * vcpumask: Pointer to bitmap of VCPUs to be flushed.
+ *
+ * cmd: MMUEXT_INVLPG_MULTI
+ * linear_addr: Linear address to be flushed.
+ * vcpumask: Pointer to bitmap of VCPUs to be flushed.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_ALL
+ * No additional arguments. Flushes all VCPUs' TLBs.
+ *
+ * cmd: MMUEXT_INVLPG_ALL
+ * linear_addr: Linear address to be flushed from all VCPUs' TLBs.
+ *
+ * cmd: MMUEXT_FLUSH_CACHE
+ * No additional arguments. Writes back and flushes cache contents.
+ *
+ * cmd: MMUEXT_FLUSH_CACHE_GLOBAL
+ * No additional arguments. Writes back and flushes cache contents
+ * on all CPUs in the system.
+ *
+ * cmd: MMUEXT_SET_LDT
+ * linear_addr: Linear address of LDT base (NB. must be page-aligned).
+ * nr_ents: Number of entries in LDT.
+ *
+ * cmd: MMUEXT_CLEAR_PAGE
+ * mfn: Machine frame number to be cleared.
+ *
+ * cmd: MMUEXT_COPY_PAGE
+ * mfn: Machine frame number of the destination page.
+ * src_mfn: Machine frame number of the source page.
+ *
+ * cmd: MMUEXT_[UN]MARK_SUPER
+ * mfn: Machine frame number of head of superpage to be [un]marked.
+ */
+#define MMUEXT_PIN_L1_TABLE      0
+#define MMUEXT_PIN_L2_TABLE      1
+#define MMUEXT_PIN_L3_TABLE      2
+#define MMUEXT_PIN_L4_TABLE      3
+#define MMUEXT_UNPIN_TABLE       4
+#define MMUEXT_NEW_BASEPTR       5
+#define MMUEXT_TLB_FLUSH_LOCAL   6
+#define MMUEXT_INVLPG_LOCAL      7
+#define MMUEXT_TLB_FLUSH_MULTI   8
+#define MMUEXT_INVLPG_MULTI      9
+#define MMUEXT_TLB_FLUSH_ALL    10
+#define MMUEXT_INVLPG_ALL       11
+#define MMUEXT_FLUSH_CACHE      12
+#define MMUEXT_SET_LDT          13
+#define MMUEXT_NEW_USER_BASEPTR 15
+#define MMUEXT_CLEAR_PAGE       16
+#define MMUEXT_COPY_PAGE        17
+#define MMUEXT_FLUSH_CACHE_GLOBAL 18
+#define MMUEXT_MARK_SUPER       19
+#define MMUEXT_UNMARK_SUPER     20
+
+#ifndef __ASSEMBLY__
+struct mmuext_op {
+	unsigned int cmd;
+	union {
+		/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
+		 * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
+		xen_pfn_t mfn;
+		/* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
+		unsigned long linear_addr;
+	} arg1;
+	union {
+		/* SET_LDT */
+		unsigned int nr_ents;
+		/* TLB_FLUSH_MULTI, INVLPG_MULTI */
+		void *vcpumask;
+		/* COPY_PAGE */
+		xen_pfn_t src_mfn;
+	} arg2;
+};
+DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
+#endif
+
+/* These are passed as 'flags' to update_va_mapping. They can be ORed. */
+/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap.   */
+/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer.         */
+#define UVMF_NONE               (0UL<<0) /* No flushing at all.   */
+#define UVMF_TLB_FLUSH          (1UL<<0) /* Flush entire TLB(s).  */
+#define UVMF_INVLPG             (2UL<<0) /* Flush only one entry. */
+#define UVMF_FLUSHTYPE_MASK     (3UL<<0)
+#define UVMF_MULTI              (0UL<<2) /* Flush subset of TLBs. */
+#define UVMF_LOCAL              (0UL<<2) /* Flush local TLB.      */
+#define UVMF_ALL                (1UL<<2) /* Flush all TLBs.       */
+
+/*
+ * Commands to HYPERVISOR_console_io().
+ */
+#define CONSOLEIO_write         0
+#define CONSOLEIO_read          1
+
+/*
+ * Commands to HYPERVISOR_vm_assist().
+ */
+#define VMASST_CMD_enable                0
+#define VMASST_CMD_disable               1
+
+/* x86/32 guests: simulate full 4GB segment limits. */
+#define VMASST_TYPE_4gb_segments         0
+
+/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
+#define VMASST_TYPE_4gb_segments_notify  1
+
+/*
+ * x86 guests: support writes to bottom-level PTEs.
+ * NB1. Page-directory entries cannot be written.
+ * NB2. Guest must continue to remove all writable mappings of PTEs.
+ */
+#define VMASST_TYPE_writable_pagetables  2
+
+/* x86/PAE guests: support PDPTs above 4GB. */
+#define VMASST_TYPE_pae_extended_cr3     3
+
+#define MAX_VMASST_TYPE 3
+
+#ifndef __ASSEMBLY__
+
+typedef uint16_t domid_t;
+
+/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
+#define DOMID_FIRST_RESERVED (0x7FF0U)
+
+/* DOMID_SELF is used in certain contexts to refer to oneself. */
+#define DOMID_SELF (0x7FF0U)
+
+/*
+ * DOMID_IO is used to restrict page-table updates to mapping I/O memory.
+ * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO
+ * is useful to ensure that no mappings to the OS's own heap are accidentally
+ * installed. (e.g., in Linux this could cause havoc as reference counts
+ * aren't adjusted on the I/O-mapping code path).
+ * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
+ * be specified by any calling domain.
+ */
+#define DOMID_IO   (0x7FF1U)
+
+/*
+ * DOMID_XEN is used to allow privileged domains to map restricted parts of
+ * Xen's heap space (e.g., the machine_to_phys table).
+ * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
+ * the caller is privileged.
+ */
+#define DOMID_XEN  (0x7FF2U)
+
+/* DOMID_COW is used as the owner of sharable pages */
+#define DOMID_COW  (0x7FF3U)
+
+/* DOMID_INVALID is used to identify pages with unknown owner. */
+#define DOMID_INVALID (0x7FF4U)
+
+/* Idle domain. */
+#define DOMID_IDLE (0x7FFFU)
+
+/*
+ * Send an array of these to HYPERVISOR_mmu_update().
+ * NB. The fields are natural pointer/address size for this architecture.
+ */
+struct mmu_update {
+    uint64_t ptr;       /* Machine address of PTE. */
+    uint64_t val;       /* New contents of PTE.    */
+};
+DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
+
+/*
+ * Send an array of these to HYPERVISOR_multicall().
+ * NB. The fields are logically the natural register size for this
+ * architecture. In cases where xen_ulong_t is larger than this then
+ * any unused bits in the upper portion must be zero.
+ */
+struct multicall_entry {
+    xen_ulong_t op;
+    xen_long_t result;
+    xen_ulong_t args[6];
+};
+DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
+
+struct vcpu_time_info {
+	/*
+	 * Updates to the following values are preceded and followed
+	 * by an increment of 'version'. The guest can therefore
+	 * detect updates by looking for changes to 'version'. If the
+	 * least-significant bit of the version number is set then an
+	 * update is in progress and the guest must wait to read a
+	 * consistent set of values.  The correct way to interact with
+	 * the version number is similar to Linux's seqlock: see the
+	 * implementations of read_seqbegin/read_seqretry.
+	 */
+	uint32_t version;
+	uint32_t pad0;
+	uint64_t tsc_timestamp;   /* TSC at last update of time vals.  */
+	uint64_t system_time;     /* Time, in nanosecs, since boot.    */
+	/*
+	 * Current system time:
+	 *   system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul
+	 * CPU frequency (Hz):
+	 *   ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift
+	 */
+	uint32_t tsc_to_system_mul;
+	int8_t   tsc_shift;
+	int8_t   pad1[3];
+}; /* 32 bytes */
+
+struct vcpu_info {
+	/*
+	 * 'evtchn_upcall_pending' is written non-zero by Xen to indicate
+	 * a pending notification for a particular VCPU. It is then cleared
+	 * by the guest OS /before/ checking for pending work, thus avoiding
+	 * a set-and-check race. Note that the mask is only accessed by Xen
+	 * on the CPU that is currently hosting the VCPU. This means that the
+	 * pending and mask flags can be updated by the guest without special
+	 * synchronisation (i.e., no need for the x86 LOCK prefix).
+	 * This may seem suboptimal because if the pending flag is set by
+	 * a different CPU then an IPI may be scheduled even when the mask
+	 * is set. However, note:
+	 *  1. The task of 'interrupt holdoff' is covered by the per-event-
+	 *     channel mask bits. A 'noisy' event that is continually being
+	 *     triggered can be masked at source at this very precise
+	 *     granularity.
+	 *  2. The main purpose of the per-VCPU mask is therefore to restrict
+	 *     reentrant execution: whether for concurrency control, or to
+	 *     prevent unbounded stack usage. Whatever the purpose, we expect
+	 *     that the mask will be asserted only for short periods at a time,
+	 *     and so the likelihood of a 'spurious' IPI is suitably small.
+	 * The mask is read before making an event upcall to the guest: a
+	 * non-zero mask therefore guarantees that the VCPU will not receive
+	 * an upcall activation. The mask is cleared when the VCPU requests
+	 * to block: this avoids wakeup-waiting races.
+	 */
+	uint8_t evtchn_upcall_pending;
+	uint8_t evtchn_upcall_mask;
+	xen_ulong_t evtchn_pending_sel;
+	struct arch_vcpu_info arch;
+	struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
+/*
+ * Xen/kernel shared data -- pointer provided in start_info.
+ * NB. We expect that this struct is smaller than a page.
+ */
+struct shared_info {
+	struct vcpu_info vcpu_info[MAX_VIRT_CPUS];
+
+	/*
+	 * A domain can create "event channels" on which it can send and receive
+	 * asynchronous event notifications. There are three classes of event that
+	 * are delivered by this mechanism:
+	 *  1. Bi-directional inter- and intra-domain connections. Domains must
+	 *     arrange out-of-band to set up a connection (usually by allocating
+	 *     an unbound 'listener' port and avertising that via a storage service
+	 *     such as xenstore).
+	 *  2. Physical interrupts. A domain with suitable hardware-access
+	 *     privileges can bind an event-channel port to a physical interrupt
+	 *     source.
+	 *  3. Virtual interrupts ('events'). A domain can bind an event-channel
+	 *     port to a virtual interrupt source, such as the virtual-timer
+	 *     device or the emergency console.
+	 *
+	 * Event channels are addressed by a "port index". Each channel is
+	 * associated with two bits of information:
+	 *  1. PENDING -- notifies the domain that there is a pending notification
+	 *     to be processed. This bit is cleared by the guest.
+	 *  2. MASK -- if this bit is clear then a 0->1 transition of PENDING
+	 *     will cause an asynchronous upcall to be scheduled. This bit is only
+	 *     updated by the guest. It is read-only within Xen. If a channel
+	 *     becomes pending while the channel is masked then the 'edge' is lost
+	 *     (i.e., when the channel is unmasked, the guest must manually handle
+	 *     pending notifications as no upcall will be scheduled by Xen).
+	 *
+	 * To expedite scanning of pending notifications, any 0->1 pending
+	 * transition on an unmasked channel causes a corresponding bit in a
+	 * per-vcpu selector word to be set. Each bit in the selector covers a
+	 * 'C long' in the PENDING bitfield array.
+	 */
+	xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8];
+	xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 8];
+
+	/*
+	 * Wallclock time: updated only by control software. Guests should base
+	 * their gettimeofday() syscall on this wallclock-base value.
+	 */
+	struct pvclock_wall_clock wc;
+
+	struct arch_shared_info arch;
+
+};
+
+/*
+ * Start-of-day memory layout for the initial domain (DOM0):
+ *  1. The domain is started within contiguous virtual-memory region.
+ *  2. The contiguous region begins and ends on an aligned 4MB boundary.
+ *  3. The region start corresponds to the load address of the OS image.
+ *     If the load address is not 4MB aligned then the address is rounded down.
+ *  4. This the order of bootstrap elements in the initial virtual region:
+ *      a. relocated kernel image
+ *      b. initial ram disk              [mod_start, mod_len]
+ *      c. list of allocated page frames [mfn_list, nr_pages]
+ *      d. start_info_t structure        [register ESI (x86)]
+ *      e. bootstrap page tables         [pt_base, CR3 (x86)]
+ *      f. bootstrap stack               [register ESP (x86)]
+ *  5. Bootstrap elements are packed together, but each is 4kB-aligned.
+ *  6. The initial ram disk may be omitted.
+ *  7. The list of page frames forms a contiguous 'pseudo-physical' memory
+ *     layout for the domain. In particular, the bootstrap virtual-memory
+ *     region is a 1:1 mapping to the first section of the pseudo-physical map.
+ *  8. All bootstrap elements are mapped read-writable for the guest OS. The
+ *     only exception is the bootstrap page table, which is mapped read-only.
+ *  9. There is guaranteed to be at least 512kB padding after the final
+ *     bootstrap element. If necessary, the bootstrap virtual region is
+ *     extended by an extra 4MB to ensure this.
+ */
+
+#define MAX_GUEST_CMDLINE 1024
+struct start_info {
+	/* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME.    */
+	char magic[32];             /* "xen-<version>-<platform>".            */
+	unsigned long nr_pages;     /* Total pages allocated to this domain.  */
+	unsigned long shared_info;  /* MACHINE address of shared info struct. */
+	uint32_t flags;             /* SIF_xxx flags.                         */
+	xen_pfn_t store_mfn;        /* MACHINE page number of shared page.    */
+	uint32_t store_evtchn;      /* Event channel for store communication. */
+	union {
+		struct {
+			xen_pfn_t mfn;      /* MACHINE page number of console page.   */
+			uint32_t  evtchn;   /* Event channel for console page.        */
+		} domU;
+		struct {
+			uint32_t info_off;  /* Offset of console_info struct.         */
+			uint32_t info_size; /* Size of console_info struct from start.*/
+		} dom0;
+	} console;
+	/* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME).     */
+	unsigned long pt_base;      /* VIRTUAL address of page directory.     */
+	unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames.       */
+	unsigned long mfn_list;     /* VIRTUAL address of page-frame list.    */
+	unsigned long mod_start;    /* VIRTUAL address of pre-loaded module.  */
+	unsigned long mod_len;      /* Size (bytes) of pre-loaded module.     */
+	int8_t cmd_line[MAX_GUEST_CMDLINE];
+	/* The pfn range here covers both page table and p->m table frames.   */
+	unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table.    */
+	unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table.  */
+};
+
+/* These flags are passed in the 'flags' field of start_info_t. */
+#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
+#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
+#define SIF_MULTIBOOT_MOD (1<<2)  /* Is mod_start a multiboot module? */
+#define SIF_MOD_START_PFN (1<<3)  /* Is mod_start a PFN? */
+#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
+
+/*
+ * A multiboot module is a package containing modules very similar to a
+ * multiboot module array. The only differences are:
+ * - the array of module descriptors is by convention simply at the beginning
+ *   of the multiboot module,
+ * - addresses in the module descriptors are based on the beginning of the
+ *   multiboot module,
+ * - the number of modules is determined by a termination descriptor that has
+ *   mod_start == 0.
+ *
+ * This permits to both build it statically and reference it in a configuration
+ * file, and let the PV guest easily rebase the addresses to virtual addresses
+ * and at the same time count the number of modules.
+ */
+struct xen_multiboot_mod_list {
+	/* Address of first byte of the module */
+	uint32_t mod_start;
+	/* Address of last byte of the module (inclusive) */
+	uint32_t mod_end;
+	/* Address of zero-terminated command line */
+	uint32_t cmdline;
+	/* Unused, must be zero */
+	uint32_t pad;
+};
+/*
+ * The console structure in start_info.console.dom0
+ *
+ * This structure includes a variety of information required to
+ * have a working VGA/VESA console.
+ */
+struct dom0_vga_console_info {
+	uint8_t video_type;
+#define XEN_VGATYPE_TEXT_MODE_3 0x03
+#define XEN_VGATYPE_VESA_LFB    0x23
+#define XEN_VGATYPE_EFI_LFB     0x70
+
+	union {
+		struct {
+			/* Font height, in pixels. */
+			uint16_t font_height;
+			/* Cursor location (column, row). */
+			uint16_t cursor_x, cursor_y;
+			/* Number of rows and columns (dimensions in characters). */
+			uint16_t rows, columns;
+		} text_mode_3;
+
+		struct {
+			/* Width and height, in pixels. */
+			uint16_t width, height;
+			/* Bytes per scan line. */
+			uint16_t bytes_per_line;
+			/* Bits per pixel. */
+			uint16_t bits_per_pixel;
+			/* LFB physical address, and size (in units of 64kB). */
+			uint32_t lfb_base;
+			uint32_t lfb_size;
+			/* RGB mask offsets and sizes, as defined by VBE 1.2+ */
+			uint8_t  red_pos, red_size;
+			uint8_t  green_pos, green_size;
+			uint8_t  blue_pos, blue_size;
+			uint8_t  rsvd_pos, rsvd_size;
+
+			/* VESA capabilities (offset 0xa, VESA command 0x4f00). */
+			uint32_t gbl_caps;
+			/* Mode attributes (offset 0x0, VESA command 0x4f01). */
+			uint16_t mode_attrs;
+		} vesa_lfb;
+	} u;
+};
+
+typedef uint64_t cpumap_t;
+
+typedef uint8_t xen_domain_handle_t[16];
+
+/* Turn a plain number into a C unsigned long constant. */
+#define __mk_unsigned_long(x) x ## UL
+#define mk_unsigned_long(x) __mk_unsigned_long(x)
+
+#define TMEM_SPEC_VERSION 1
+
+struct tmem_op {
+	uint32_t cmd;
+	int32_t pool_id;
+	union {
+		struct {  /* for cmd == TMEM_NEW_POOL */
+			uint64_t uuid[2];
+			uint32_t flags;
+		} new;
+		struct {
+			uint64_t oid[3];
+			uint32_t index;
+			uint32_t tmem_offset;
+			uint32_t pfn_offset;
+			uint32_t len;
+			GUEST_HANDLE(void) gmfn; /* guest machine page frame */
+		} gen;
+	} u;
+};
+
+DEFINE_GUEST_HANDLE(u64);
+
+#else /* __ASSEMBLY__ */
+
+/* In assembly code we cannot use C numeric constant suffixes. */
+#define mk_unsigned_long(x) x
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __XEN_PUBLIC_XEN_H__ */