24 files changed, 1057 insertions, 186 deletions

diff --git a/CREDITS b/CREDITS
index 206d0fcf07a5..646a0a9ad6d1 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1120,6 +1120,7 @@ D: author of userfs filesystem
 D: Improved mmap and munmap handling
 D: General mm minor tidyups
 D: autofs v4 maintainer
+D: Xen subsystem
 S: 987 Alabama St
 S: San Francisco
 S: CA, 94110
diff --git a/Documentation/tpm/xen-tpmfront.txt b/Documentation/tpm/xen-tpmfront.txt
new file mode 100644
index 000000000000..69346de87ff3
--- /dev/null
+++ b/Documentation/tpm/xen-tpmfront.txt
@@ -0,0 +1,113 @@
+Virtual TPM interface for Xen
+
+Authors: Matthew Fioravante (JHUAPL), Daniel De Graaf (NSA)
+
+This document describes the virtual Trusted Platform Module (vTPM) subsystem for
+Xen. The reader is assumed to have familiarity with building and installing Xen,
+Linux, and a basic understanding of the TPM and vTPM concepts.
+
+INTRODUCTION
+
+The goal of this work is to provide a TPM functionality to a virtual guest
+operating system (in Xen terms, a DomU).  This allows programs to interact with
+a TPM in a virtual system the same way they interact with a TPM on the physical
+system.  Each guest gets its own unique, emulated, software TPM.  However, each
+of the vTPM's secrets (Keys, NVRAM, etc) are managed by a vTPM Manager domain,
+which seals the secrets to the Physical TPM.  If the process of creating each of
+these domains (manager, vTPM, and guest) is trusted, the vTPM subsystem extends
+the chain of trust rooted in the hardware TPM to virtual machines in Xen. Each
+major component of vTPM is implemented as a separate domain, providing secure
+separation guaranteed by the hypervisor. The vTPM domains are implemented in
+mini-os to reduce memory and processor overhead.
+
+This mini-os vTPM subsystem was built on top of the previous vTPM work done by
+IBM and Intel corporation.
+
+
+DESIGN OVERVIEW
+---------------
+
+The architecture of vTPM is described below:
+
++------------------+
+|    Linux DomU    | ...
+|       |  ^       |
+|       v  |       |
+|   xen-tpmfront   |
++------------------+
+        |  ^
+        v  |
++------------------+
+| mini-os/tpmback  |
+|       |  ^       |
+|       v  |       |
+|  vtpm-stubdom    | ...
+|       |  ^       |
+|       v  |       |
+| mini-os/tpmfront |
++------------------+
+        |  ^
+        v  |
++------------------+
+| mini-os/tpmback  |
+|       |  ^       |
+|       v  |       |
+| vtpmmgr-stubdom  |
+|       |  ^       |
+|       v  |       |
+| mini-os/tpm_tis  |
++------------------+
+        |  ^
+        v  |
++------------------+
+|   Hardware TPM   |
++------------------+
+
+ * Linux DomU: The Linux based guest that wants to use a vTPM. There may be
+	       more than one of these.
+
+ * xen-tpmfront.ko: Linux kernel virtual TPM frontend driver. This driver
+                    provides vTPM access to a Linux-based DomU.
+
+ * mini-os/tpmback: Mini-os TPM backend driver. The Linux frontend driver
+		    connects to this backend driver to facilitate communications
+		    between the Linux DomU and its vTPM. This driver is also
+		    used by vtpmmgr-stubdom to communicate with vtpm-stubdom.
+
+ * vtpm-stubdom: A mini-os stub domain that implements a vTPM. There is a
+		 one to one mapping between running vtpm-stubdom instances and
+                 logical vtpms on the system. The vTPM Platform Configuration
+                 Registers (PCRs) are normally all initialized to zero.
+
+ * mini-os/tpmfront: Mini-os TPM frontend driver. The vTPM mini-os domain
+		     vtpm-stubdom uses this driver to communicate with
+		     vtpmmgr-stubdom. This driver is also used in mini-os
+		     domains such as pv-grub that talk to the vTPM domain.
+
+ * vtpmmgr-stubdom: A mini-os domain that implements the vTPM manager. There is
+		    only one vTPM manager and it should be running during the
+		    entire lifetime of the machine.  This domain regulates
+		    access to the physical TPM on the system and secures the
+		    persistent state of each vTPM.
+
+ * mini-os/tpm_tis: Mini-os TPM version 1.2 TPM Interface Specification (TIS)
+                    driver. This driver used by vtpmmgr-stubdom to talk directly to
+                    the hardware TPM. Communication is facilitated by mapping
+                    hardware memory pages into vtpmmgr-stubdom.
+
+ * Hardware TPM: The physical TPM that is soldered onto the motherboard.
+
+
+INTEGRATION WITH XEN
+--------------------
+
+Support for the vTPM driver was added in Xen using the libxl toolstack in Xen
+4.3.  See the Xen documentation (docs/misc/vtpm.txt) for details on setting up
+the vTPM and vTPM Manager stub domains.  Once the stub domains are running, a
+vTPM device is set up in the same manner as a disk or network device in the
+domain's configuration file.
+
+In order to use features such as IMA that require a TPM to be loaded prior to
+the initrd, the xen-tpmfront driver must be compiled in to the kernel.  If not
+using such features, the driver can be compiled as a module and will be loaded
+as usual.
diff --git a/MAINTAINERS b/MAINTAINERS
index 49a692e2aa57..4bb5689000f8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9278,9 +9278,9 @@ F:	drivers/media/tuners/tuner-xc2028.*
 
 XEN HYPERVISOR INTERFACE
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-M:	Jeremy Fitzhardinge <jeremy@goop.org>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
-L:	virtualization@lists.linux-foundation.org
+M:	Boris Ostrovsky <boris.ostrovsky@oracle.com>
+M:	David Vrabel <david.vrabel@citrix.com>
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/xen/
 F:	drivers/*/xen-*front.c
@@ -9291,35 +9291,35 @@ F:	include/uapi/xen/
 
 XEN HYPERVISOR ARM
 M:	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/arm/xen/
 F:	arch/arm/include/asm/xen/
 
 XEN HYPERVISOR ARM64
 M:	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/arm64/xen/
 F:	arch/arm64/include/asm/xen/
 
 XEN NETWORK BACKEND DRIVER
 M:	Ian Campbell <ian.campbell@citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/xen-netback/*
 
 XEN PCI SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/pci/*xen*
 F:	drivers/pci/*xen*
 
 XEN SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index ca842f2769ef..608a79d5a466 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -7,6 +7,7 @@ enum ipi_vector {
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 	XEN_SPIN_UNLOCK_VECTOR,
 	XEN_IRQ_WORK_VECTOR,
+	XEN_NMI_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2fcaedc0b739..2fc216dfbd9c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -427,8 +427,7 @@ static void __init xen_init_cpuid_mask(void)
 
 	if (!xen_initial_domain())
 		cpuid_leaf1_edx_mask &=
-			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
-			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
+			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */
 
 	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
 
@@ -735,8 +734,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		addr = (unsigned long)xen_int3;
 	else if (addr == (unsigned long)stack_segment)
 		addr = (unsigned long)xen_stack_segment;
-	else if (addr == (unsigned long)double_fault ||
-		 addr == (unsigned long)nmi) {
+	else if (addr == (unsigned long)double_fault) {
 		/* Don't need to handle these */
 		return 0;
 #ifdef CONFIG_X86_MCE
@@ -747,7 +745,12 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		 */
 		;
 #endif
-	} else {
+	} else if (addr == (unsigned long)nmi)
+		/*
+		 * Use the native version as well.
+		 */
+		;
+	else {
 		/* Some other trap using IST? */
 		if (WARN_ON(val->ist != 0))
 			return 0;
@@ -1710,6 +1713,8 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_hvm_init_shared_info();
 
+	xen_panic_handler_init();
+
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 	xen_hvm_smp_init();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 01a4dc015ae1..0da7f863056f 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -47,23 +47,18 @@ static void xen_restore_fl(unsigned long flags)
 	/* convert from IF type flag */
 	flags = !(flags & X86_EFLAGS_IF);
 
-	/* There's a one instruction preempt window here.  We need to
-	   make sure we're don't switch CPUs between getting the vcpu
-	   pointer and updating the mask. */
+	/* See xen_irq_enable() for why preemption must be disabled. */
 	preempt_disable();
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = flags;
-	preempt_enable_no_resched();
-
-	/* Doesn't matter if we get preempted here, because any
-	   pending event will get dealt with anyway. */
 
 	if (flags == 0) {
-		preempt_check_resched();
 		barrier(); /* unmask then check (avoid races) */
 		if (unlikely(vcpu->evtchn_upcall_pending))
 			xen_force_evtchn_callback();
-	}
+		preempt_enable();
+	} else
+		preempt_enable_no_resched();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
 
@@ -82,10 +77,12 @@ static void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
-	/* We don't need to worry about being preempted here, since
-	   either a) interrupts are disabled, so no preemption, or b)
-	   the caller is confused and is trying to re-enable interrupts
-	   on an indeterminate processor. */
+	/*
+	 * We may be preempted as soon as vcpu->evtchn_upcall_mask is
+	 * cleared, so disable preemption to ensure we check for
+	 * events on the VCPU we are still running on.
+	 */
+	preempt_disable();
 
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = 0;
@@ -96,6 +93,8 @@ static void xen_irq_enable(void)
 	barrier(); /* unmask then check (avoid races) */
 	if (unlikely(vcpu->evtchn_upcall_pending))
 		xen_force_evtchn_callback();
+
+	preempt_enable();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa5927e..0d4ec35895d4 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,6 +161,7 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/balloon.h>
 #include <xen/grant_table.h>
 
 #include "multicalls.h"
@@ -967,7 +968,10 @@ int m2p_remove_override(struct page *page,
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
-			struct gnttab_unmap_grant_ref *unmap_op;
+			struct gnttab_unmap_and_replace *unmap_op;
+			struct page *scratch_page = get_balloon_scratch_page();
+			unsigned long scratch_page_address = (unsigned long)
+				__va(page_to_pfn(scratch_page) << PAGE_SHIFT);
 
 			/*
 			 * It might be that we queued all the m2p grant table
@@ -990,21 +994,25 @@ int m2p_remove_override(struct page *page,
 			}
 
 			mcs = xen_mc_entry(
-					sizeof(struct gnttab_unmap_grant_ref));
+					sizeof(struct gnttab_unmap_and_replace));
 			unmap_op = mcs.args;
 			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->new_addr = scratch_page_address;
 			unmap_op->handle = kmap_op->handle;
-			unmap_op->dev_bus_addr = 0;
 
 			MULTI_grant_table_op(mcs.mc,
-					GNTTABOP_unmap_grant_ref, unmap_op, 1);
+					GNTTABOP_unmap_and_replace, unmap_op, 1);
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 
-			set_pte_at(&init_mm, address, ptep,
-					pfn_pte(pfn, PAGE_KERNEL));
-			__flush_tlb_single(address);
+			mcs = __xen_mc_entry(0);
+			MULTI_update_va_mapping(mcs.mc, scratch_page_address,
+					pfn_pte(page_to_pfn(get_balloon_scratch_page()),
+					PAGE_KERNEL_RO), 0);
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+
 			kmap_op->host_addr = 0;
+			put_balloon_scratch_page();
 		}
 	}
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8f3eea6b80c5..09f3059cb00b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -33,6 +33,9 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
+#ifdef CONFIG_X86_64
+extern const char nmi[];
+#endif
 extern void xen_sysenter_target(void);
 extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
@@ -215,13 +218,19 @@ static void __init xen_set_identity_and_release_chunk(
 	unsigned long pfn;
 
 	/*
-	 * If the PFNs are currently mapped, the VA mapping also needs
-	 * to be updated to be 1:1.
+	 * If the PFNs are currently mapped, clear the mappings
+	 * (except for the ISA region which must be 1:1 mapped) to
+	 * release the refcounts (in Xen) on the original frames.
 	 */
-	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+		pte_t pte = __pte_ma(0);
+
+		if (pfn < PFN_UP(ISA_END_ADDRESS))
+			pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+
 		(void)HYPERVISOR_update_va_mapping(
-			(unsigned long)__va(pfn << PAGE_SHIFT),
-			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+			(unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+	}
 
 	if (start_pfn < nr_pages)
 		*released += xen_release_chunk(
@@ -547,7 +556,13 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-
+void __cpuinit xen_enable_nmi(void)
+{
+#ifdef CONFIG_X86_64
+	if (register_callback(CALLBACKTYPE_nmi, nmi))
+		BUG();
+#endif
+}
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
@@ -565,7 +580,7 @@ void __init xen_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-
+	xen_enable_nmi();
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
 		printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 597655bd72b0..9235842cd76a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -573,6 +573,12 @@ static inline int xen_map_vector(int vector)
 	case IRQ_WORK_VECTOR:
 		xen_vector = XEN_IRQ_WORK_VECTOR;
 		break;
+#ifdef CONFIG_X86_64
+	case NMI_VECTOR:
+	case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */
+		xen_vector = XEN_NMI_VECTOR;
+		break;
+#endif
 	default:
 		xen_vector = -1;
 		printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index dbfd56446c31..94c0c74434ea 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -91,4 +91,16 @@ config TCG_ST33_I2C
         To compile this driver as a module, choose M here; the module will be
         called tpm_stm_st33_i2c.
 
+config TCG_XEN
+	tristate "XEN TPM Interface"
+	depends on TCG_TPM && XEN
+	select XEN_XENBUS_FRONTEND
+	---help---
+	  If you want to make TPM support available to a Xen user domain,
+	  say Yes and it will be accessible from within Linux. See
+	  the manpages for xl, xl.conf, and docs/misc/vtpm.txt in
+	  the Xen source repository for more details.
+	  To compile this driver as a module, choose M here; the module
+	  will be called xen-tpmfront.
+
 endif # TCG_TPM
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index a3736c97c65a..eb41ff97d0ad 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_TCG_ATMEL) += tpm_atmel.o
 obj-$(CONFIG_TCG_INFINEON) += tpm_infineon.o
 obj-$(CONFIG_TCG_IBMVTPM) += tpm_ibmvtpm.o
 obj-$(CONFIG_TCG_ST33_I2C) += tpm_i2c_stm_st33.o
+obj-$(CONFIG_TCG_XEN) += xen-tpmfront.o
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
new file mode 100644
index 000000000000..7a7929ba2658
--- /dev/null
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -0,0 +1,473 @@
+/*
+ * Implementation of the Xen vTPM device frontend
+ *
+ * Author:  Daniel De Graaf <dgdegra@tycho.nsa.gov>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <xen/events.h>
+#include <xen/interface/io/tpmif.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/page.h>
+#include "tpm.h"
+
+struct tpm_private {
+	struct tpm_chip *chip;
+	struct xenbus_device *dev;
+
+	struct vtpm_shared_page *shr;
+
+	unsigned int evtchn;
+	int ring_ref;
+	domid_t backend_id;
+};
+
+enum status_bits {
+	VTPM_STATUS_RUNNING  = 0x1,
+	VTPM_STATUS_IDLE     = 0x2,
+	VTPM_STATUS_RESULT   = 0x4,
+	VTPM_STATUS_CANCELED = 0x8,
+};
+
+static u8 vtpm_status(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_CANCELED;
+	case VTPM_STATE_FINISH:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_RESULT;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL: /* cancel requested, not yet canceled */
+		return VTPM_STATUS_RUNNING;
+	default:
+		return 0;
+	}
+}
+
+static bool vtpm_req_canceled(struct tpm_chip *chip, u8 status)
+{
+	return status & VTPM_STATUS_CANCELED;
+}
+
+static void vtpm_cancel(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	priv->shr->state = VTPM_STATE_CANCEL;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+}
+
+static unsigned int shr_data_offset(struct vtpm_shared_page *shr)
+{
+	return sizeof(*shr) + sizeof(u32) * shr->nr_extra_pages;
+}
+
+static int vtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+
+	u32 ordinal;
+	unsigned long duration;
+
+	if (offset > PAGE_SIZE)
+		return -EINVAL;
+
+	if (offset + count > PAGE_SIZE)
+		return -EINVAL;
+
+	/* Wait for completion of any existing command or cancellation */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	memcpy(offset + (u8 *)shr, buf, count);
+	shr->length = count;
+	barrier();
+	shr->state = VTPM_STATE_SUBMIT;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+
+	ordinal = be32_to_cpu(((struct tpm_input_header*)buf)->ordinal);
+	duration = tpm_calc_ordinal_duration(chip, ordinal);
+
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, duration,
+			&chip->vendor.read_queue, true) < 0) {
+		/* got a signal or timeout, try to cancel */
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	return count;
+}
+
+static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+	size_t length = shr->length;
+
+	if (shr->state == VTPM_STATE_IDLE)
+		return -ECANCELED;
+
+	/* In theory the wait at the end of _send makes this one unnecessary */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_RESULT, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	if (offset > PAGE_SIZE)
+		return -EIO;
+
+	if (offset + length > PAGE_SIZE)
+		length = PAGE_SIZE - offset;
+
+	if (length > count)
+		length = count;
+
+	memcpy(buf, offset + (u8 *)shr, length);
+
+	return length;
+}
+
+ssize_t tpm_show_locality(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	u8 locality = priv->shr->locality;
+
+	return sprintf(buf, "%d\n", locality);
+}
+
+ssize_t tpm_store_locality(struct device *dev, struct device_attribute *attr,
+			const char *buf, size_t len)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	u8 val;
+
+	int rv = kstrtou8(buf, 0, &val);
+	if (rv)
+		return rv;
+
+	priv->shr->locality = val;
+
+	return len;
+}
+
+static const struct file_operations vtpm_ops = {
+	.owner = THIS_MODULE,
+	.llseek = no_llseek,
+	.open = tpm_open,
+	.read = tpm_read,
+	.write = tpm_write,
+	.release = tpm_release,
+};
+
+static DEVICE_ATTR(pubek, S_IRUGO, tpm_show_pubek, NULL);
+static DEVICE_ATTR(pcrs, S_IRUGO, tpm_show_pcrs, NULL);
+static DEVICE_ATTR(enabled, S_IRUGO, tpm_show_enabled, NULL);
+static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
+static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
+static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated,
+		NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
+static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
+static DEVICE_ATTR(locality, S_IRUGO | S_IWUSR, tpm_show_locality,
+		tpm_store_locality);
+
+static struct attribute *vtpm_attrs[] = {
+	&dev_attr_pubek.attr,
+	&dev_attr_pcrs.attr,
+	&dev_attr_enabled.attr,
+	&dev_attr_active.attr,
+	&dev_attr_owned.attr,
+	&dev_attr_temp_deactivated.attr,
+	&dev_attr_caps.attr,
+	&dev_attr_cancel.attr,
+	&dev_attr_durations.attr,
+	&dev_attr_timeouts.attr,
+	&dev_attr_locality.attr,
+	NULL,
+};
+
+static struct attribute_group vtpm_attr_grp = {
+	.attrs = vtpm_attrs,
+};
+
+#define TPM_LONG_TIMEOUT   (10 * 60 * HZ)
+
+static const struct tpm_vendor_specific tpm_vtpm = {
+	.status = vtpm_status,
+	.recv = vtpm_recv,
+	.send = vtpm_send,
+	.cancel = vtpm_cancel,
+	.req_complete_mask = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_complete_val  = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_canceled      = vtpm_req_canceled,
+	.attr_group = &vtpm_attr_grp,
+	.miscdev = {
+		.fops = &vtpm_ops,
+	},
+	.duration = {
+		TPM_LONG_TIMEOUT,
+		TPM_LONG_TIMEOUT,
+		TPM_LONG_TIMEOUT,
+	},
+};
+
+static irqreturn_t tpmif_interrupt(int dummy, void *dev_id)
+{
+	struct tpm_private *priv = dev_id;
+
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+	case VTPM_STATE_FINISH:
+		wake_up_interruptible(&priv->chip->vendor.read_queue);
+		break;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL:
+	default:
+		break;
+	}
+	return IRQ_HANDLED;
+}
+
+static int setup_chip(struct device *dev, struct tpm_private *priv)
+{
+	struct tpm_chip *chip;
+
+	chip = tpm_register_hardware(dev, &tpm_vtpm);
+	if (!chip)
+		return -ENODEV;
+
+	init_waitqueue_head(&chip->vendor.read_queue);
+
+	priv->chip = chip;
+	TPM_VPRIV(chip) = priv;
+
+	return 0;
+}
+
+/* caller must clean up in case of errors */
+static int setup_ring(struct xenbus_device *dev, struct tpm_private *priv)
+{
+	struct xenbus_transaction xbt;
+	const char *message = NULL;
+	int rv;
+
+	priv->shr = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!priv->shr) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
+		return -ENOMEM;
+	}
+
+	rv = xenbus_grant_ring(dev, virt_to_mfn(priv->shr));
+	if (rv < 0)
+		return rv;
+
+	priv->ring_ref = rv;
+
+	rv = xenbus_alloc_evtchn(dev, &priv->evtchn);
+	if (rv)
+		return rv;
+
+	rv = bind_evtchn_to_irqhandler(priv->evtchn, tpmif_interrupt, 0,
+				       "tpmif", priv);
+	if (rv <= 0) {
+		xenbus_dev_fatal(dev, rv, "allocating TPM irq");
+		return rv;
+	}
+	priv->chip->vendor.irq = rv;
+
+ again:
+	rv = xenbus_transaction_start(&xbt);
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "starting transaction");
+		return rv;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename,
+			"ring-ref", "%u", priv->ring_ref);
+	if (rv) {
+		message = "writing ring-ref";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "event-channel", "%u",
+			priv->evtchn);
+	if (rv) {
+		message = "writing event-channel";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "feature-protocol-v2", "1");
+	if (rv) {
+		message = "writing feature-protocol-v2";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_transaction_end(xbt, 0);
+	if (rv == -EAGAIN)
+		goto again;
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "completing transaction");
+		return rv;
+	}
+
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+ abort_transaction:
+	xenbus_transaction_end(xbt, 1);
+	if (message)
+		xenbus_dev_error(dev, rv, "%s", message);
+
+	return rv;
+}
+
+static void ring_free(struct tpm_private *priv)
+{
+	if (!priv)
+		return;
+
+	if (priv->ring_ref)
+		gnttab_end_foreign_access(priv->ring_ref, 0,
+				(unsigned long)priv->shr);
+	else
+		free_page((unsigned long)priv->shr);
+
+	if (priv->chip && priv->chip->vendor.irq)
+		unbind_from_irqhandler(priv->chip->vendor.irq, priv);
+
+	kfree(priv);
+}
+
+static int tpmfront_probe(struct xenbus_device *dev,
+		const struct xenbus_device_id *id)
+{
+	struct tpm_private *priv;
+	int rv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating priv structure");
+		return -ENOMEM;
+	}
+
+	rv = setup_chip(&dev->dev, priv);
+	if (rv) {
+		kfree(priv);
+		return rv;
+	}
+
+	rv = setup_ring(dev, priv);
+	if (rv) {
+		tpm_remove_hardware(&dev->dev);
+		ring_free(priv);
+		return rv;
+	}
+
+	tpm_get_timeouts(priv->chip);
+
+	dev_set_drvdata(&dev->dev, priv->chip);
+
+	return rv;
+}
+
+static int tpmfront_remove(struct xenbus_device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	tpm_remove_hardware(&dev->dev);
+	ring_free(priv);
+	TPM_VPRIV(chip) = NULL;
+	return 0;
+}
+
+static int tpmfront_resume(struct xenbus_device *dev)
+{
+	/* A suspend/resume/migrate will interrupt a vTPM anyway */
+	tpmfront_remove(dev);
+	return tpmfront_probe(dev, NULL);
+}
+
+static void backend_changed(struct xenbus_device *dev,
+		enum xenbus_state backend_state)
+{
+	int val;
+
+	switch (backend_state) {
+	case XenbusStateInitialised:
+	case XenbusStateConnected:
+		if (dev->state == XenbusStateConnected)
+			break;
+
+		if (xenbus_scanf(XBT_NIL, dev->otherend,
+				"feature-protocol-v2", "%d", &val) < 0)
+			val = 0;
+		if (!val) {
+			xenbus_dev_fatal(dev, -EINVAL,
+					"vTPM protocol 2 required");
+			return;
+		}
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+	case XenbusStateClosed:
+		device_unregister(&dev->dev);
+		xenbus_frontend_closed(dev);
+		break;
+	default:
+		break;
+	}
+}
+
+static const struct xenbus_device_id tpmfront_ids[] = {
+	{ "vtpm" },
+	{ "" }
+};
+MODULE_ALIAS("xen:vtpm");
+
+static DEFINE_XENBUS_DRIVER(tpmfront, ,
+		.probe = tpmfront_probe,
+		.remove = tpmfront_remove,
+		.resume = tpmfront_resume,
+		.otherend_changed = backend_changed,
+	);
+
+static int __init xen_tpmfront_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	return xenbus_register_frontend(&tpmfront_driver);
+}
+module_init(xen_tpmfront_init);
+
+static void __exit xen_tpmfront_exit(void)
+{
+	xenbus_unregister_driver(&tpmfront_driver);
+}
+module_exit(xen_tpmfront_exit);
+
+MODULE_AUTHOR("Daniel De Graaf <dgdegra@tycho.nsa.gov>");
+MODULE_DESCRIPTION("Xen vTPM Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 2a2ef97697b2..3101cf6daf56 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -38,6 +38,7 @@
 
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
@@ -52,6 +53,7 @@
 #include <linux/notifier.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/percpu-defs.h>
 
 #i