Merge tag 'for-linus-4.12b-rc0b-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
"Xen fixes and featrues for 4.12. The main changes are:

- enable building the kernel with Xen support but without enabling
paravirtualized mode (Vitaly Kuznetsov)

- add a new 9pfs xen frontend driver (Stefano Stabellini)

- simplify Xen's cpuid handling by making use of cpu capabilities
(Juergen Gross)

- add/modify some headers for new Xen paravirtualized devices
(Oleksandr Andrushchenko)

- EFI reset_system support under Xen (Julien Grall)

- and the usual cleanups and corrections"

* tag 'for-linus-4.12b-rc0b-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (57 commits)
xen: Move xen_have_vector_callback definition to enlighten.c
xen: Implement EFI reset_system callback
arm/xen: Consolidate calls to shutdown hypercall in a single helper
xen: Export xen_reboot
xen/x86: Call xen_smp_intr_init_pv() on BSP
xen: Revert commits da72ff5bfcb0 and 72a9b186292d
xen/pvh: Do not fill kernel's e820 map in init_pvh_bootparams()
xen/scsifront: use offset_in_page() macro
xen/arm,arm64: rename __generic_dma_ops to xen_get_dma_ops
xen/arm,arm64: fix xen_dma_ops after 815dd18 "Consolidate get_dma_ops..."
xen/9pfs: select CONFIG_XEN_XENBUS_FRONTEND
x86/cpu: remove hypervisor specific set_cpu_features
vmware: set cpu capabilities during platform initialization
x86/xen: use capabilities instead of fake cpuid values for xsave
x86/xen: use capabilities instead of fake cpuid values for x2apic
x86/xen: use capabilities instead of fake cpuid values for mwait
x86/xen: use capabilities instead of fake cpuid values for acpi
x86/xen: use capabilities instead of fake cpuid values for acc
x86/xen: use capabilities instead of fake cpuid values for mtrr
x86/xen: use capabilities instead of fake cpuid values for aperf
...

arch/arm/include/asm/device.h

···
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
 #endif
+#ifdef CONFIG_XEN
+	const struct dma_map_ops *dev_dma_ops;
+#endif
 	bool dma_coherent;
 };
 

arch/arm/include/asm/dma-mapping.h

···
 extern const struct dma_map_ops arm_dma_ops;
 extern const struct dma_map_ops arm_coherent_dma_ops;
 
-static inline const struct dma_map_ops *__generic_dma_ops(struct device *dev)
-{
-	if (dev && dev->dma_ops)
-		return dev->dma_ops;
-	return &arm_dma_ops;
-}
-
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	if (xen_initial_domain())
-		return xen_dma_ops;
-	else
-		return __generic_dma_ops(NULL);
+	return &arm_dma_ops;
 }
 
 #define HAVE_ARCH_DMA_SUPPORTED 1

arch/arm/mm/dma-mapping.c

···
 		dma_ops = arm_get_dma_map_ops(coherent);
 
 	set_dma_ops(dev, dma_ops);
+
+#ifdef CONFIG_XEN
+	if (xen_initial_domain()) {
+		dev->archdata.dev_dma_ops = dev->dma_ops;
+		dev->dma_ops = xen_dma_ops;
+	}
+#endif
 }
 
 void arch_teardown_dma_ops(struct device *dev)

arch/arm/xen/efi.c

···
 	efi.update_capsule           = xen_efi_update_capsule;
 	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
 	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-	efi.reset_system             = NULL; /* Functionality provided by Xen. */
+	efi.reset_system             = xen_efi_reset_system;
 }
 EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);

arch/arm/xen/enlighten.c

···
 	return 0;
 }
 
-static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
+void xen_reboot(int reason)
 {
-	struct sched_shutdown r = { .reason = SHUTDOWN_reboot };
+	struct sched_shutdown r = { .reason = reason };
 	int rc;
+
 	rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
 	BUG_ON(rc);
 }
 
+static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
+{
+	xen_reboot(SHUTDOWN_reboot);
+}
+
+
 static void xen_power_off(void)
 {
-	struct sched_shutdown r = { .reason = SHUTDOWN_poweroff };
-	int rc;
-	rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
-	BUG_ON(rc);
+	xen_reboot(SHUTDOWN_poweroff);
 }
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)

arch/arm64/include/asm/device.h

···
 #ifdef CONFIG_IOMMU_API
 	void *iommu;			/* private IOMMU data */
 #endif
+#ifdef CONFIG_XEN
+	const struct dma_map_ops *dev_dma_ops;
+#endif
 	bool dma_coherent;
 };
 

arch/arm64/include/asm/dma-mapping.h

···
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern const struct dma_map_ops dummy_dma_ops;
 
-static inline const struct dma_map_ops *__generic_dma_ops(struct device *dev)
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	if (dev && dev->dma_ops)
-		return dev->dma_ops;
-
 	/*
 	 * We expect no ISA devices, and all other DMA masters are expected to
 	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
-}
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	if (xen_initial_domain())
-		return xen_dma_ops;
-	else
-		return __generic_dma_ops(NULL);
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,

arch/arm64/mm/dma-mapping.c

···
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
+
+#ifdef CONFIG_XEN
+	if (xen_initial_domain()) {
+		dev->archdata.dev_dma_ops = dev->dma_ops;
+		dev->dma_ops = xen_dma_ops;
+	}
+#endif
 }

arch/x86/include/asm/hypervisor.h

···
 	/* Detection routine */
 	uint32_t	(*detect)(void);
 
-	/* Adjust CPU feature bits (run once per CPU) */
-	void		(*set_cpu_features)(struct cpuinfo_x86 *);
-
 	/* Platform setup (run once per boot) */
 	void		(*init_platform)(void);
 
···
 /* Recognized hypervisors */
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
-extern const struct hypervisor_x86 x86_hyper_xen;
+extern const struct hypervisor_x86 x86_hyper_xen_pv;
+extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 extern const struct hypervisor_x86 x86_hyper_kvm;
 
-extern void init_hypervisor(struct cpuinfo_x86 *c);
 extern void init_hypervisor_platform(void);
 extern bool hypervisor_x2apic_available(void);
 extern void hypervisor_pin_vcpu(int cpu);
 #else
-static inline void init_hypervisor(struct cpuinfo_x86 *c) { }
 static inline void init_hypervisor_platform(void) { }
 static inline bool hypervisor_x2apic_available(void) { return false; }
 #endif /* CONFIG_HYPERVISOR_GUEST */

arch/x86/include/asm/xen/events.h

···
 /* No need for a barrier -- XCHG is a barrier on x86. */
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
+extern int xen_have_vector_callback;
+
+/*
+ * Events delivered via platform PCI interrupts are always
+ * routed to vcpu 0 and hence cannot be rebound.
+ */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return (!xen_hvm_domain() || xen_have_vector_callback);
+}
+
 #endif /* _ASM_X86_XEN_EVENTS_H */

arch/x86/include/asm/xen/page.h

···
 extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 						    unsigned long pfn_e);
 
+#ifdef CONFIG_XEN_PV
 extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
 				   struct page **pages, unsigned int count);
 extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 				     struct gnttab_unmap_grant_ref *kunmap_ops,
 				     struct page **pages, unsigned int count);
+#else
+static inline int
+set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+			struct gnttab_map_grant_ref *kmap_ops,
+			struct page **pages, unsigned int count)
+{
+	return 0;
+}
+
+static inline int
+clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
+			  struct gnttab_unmap_grant_ref *kunmap_ops,
+			  struct page **pages, unsigned int count)
+{
+	return 0;
+}
+#endif
 
 /*
  * Helper functions to write or read unsigned long values to/from
···
 	return __get_user(*val, (unsigned long __user *)addr);
 }
 
+#ifdef CONFIG_XEN_PV
 /*
  * When to use pfn_to_mfn(), __pfn_to_mfn() or get_phys_to_machine():
  * - pfn_to_mfn() returns either INVALID_P2M_ENTRY or the mfn. No indicator
···
 
 	return mfn;
 }
+#else
+static inline unsigned long __pfn_to_mfn(unsigned long pfn)
+{
+	return pfn;
+}
+#endif
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {

arch/x86/kernel/cpu/common.c

···
 	detect_ht(c);
 #endif
 
-	init_hypervisor(c);
 	x86_init_rdrand(c);
 	x86_init_cache_qos(c);
 	setup_pku(c);

arch/x86/kernel/cpu/hypervisor.c

···
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
-#ifdef CONFIG_XEN
-	&x86_hyper_xen,
+#ifdef CONFIG_XEN_PV
+	&x86_hyper_xen_pv,
+#endif
+#ifdef CONFIG_XEN_PVHVM
+	&x86_hyper_xen_hvm,
 #endif
 	&x86_hyper_vmware,
 	&x86_hyper_ms_hyperv,
···
 		pr_info("Hypervisor detected: %s\n", x86_hyper->name);
 }
 
-void init_hypervisor(struct cpuinfo_x86 *c)
-{
-	if (x86_hyper && x86_hyper->set_cpu_features)
-		x86_hyper->set_cpu_features(c);
-}
-
 void __init init_hypervisor_platform(void)
 {
 
···
 
 	if (!x86_hyper)
 		return;
-
-	init_hypervisor(&boot_cpu_data);
 
 	if (x86_hyper->init_platform)
 		x86_hyper->init_platform();

arch/x86/kernel/cpu/vmware.c

···
 #define vmware_paravirt_ops_setup() do {} while (0)
 #endif
 
+/*
+ * VMware hypervisor takes care of exporting a reliable TSC to the guest.
+ * Still, due to timing difference when running on virtual cpus, the TSC can
+ * be marked as unstable in some cases. For example, the TSC sync check at
+ * bootup can fail due to a marginal offset between vcpus' TSCs (though the
+ * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
+ * is not suitable as a watchdog when running on a hypervisor because the
+ * kernel may miss a wrap of the counter if the vcpu is descheduled for a
+ * long time. To skip these checks at runtime we set these capability bits,
+ * so that the kernel could just trust the hypervisor with providing a
+ * reliable virtual TSC that is suitable for timekeeping.
+ */
+static void __init vmware_set_capabilities(void)
+{
+	setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC);
+	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+}
+
 static void __init vmware_platform_setup(void)
 {
 	uint32_t eax, ebx, ecx, edx;
···
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif
+
+	vmware_set_capabilities();
 }
 
 /*
···
 	return 0;
 }
 
-/*
- * VMware hypervisor takes care of exporting a reliable TSC to the guest.
- * Still, due to timing difference when running on virtual cpus, the TSC can
- * be marked as unstable in some cases. For example, the TSC sync check at
- * bootup can fail due to a marginal offset between vcpus' TSCs (though the
- * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
- * is not suitable as a watchdog when running on a hypervisor because the
- * kernel may miss a wrap of the counter if the vcpu is descheduled for a
- * long time. To skip these checks at runtime we set these capability bits,
- * so that the kernel could just trust the hypervisor with providing a
- * reliable virtual TSC that is suitable for timekeeping.
- */
-static void vmware_set_cpu_features(struct cpuinfo_x86 *c)
-{
-	set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-	set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
-}
-
 /* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */
 static bool __init vmware_legacy_x2apic_available(void)
 {
···
 const __refconst struct hypervisor_x86 x86_hyper_vmware = {
 	.name			= "VMware",
 	.detect			= vmware_platform,
-	.set_cpu_features	= vmware_set_cpu_features,
 	.init_platform		= vmware_platform_setup,
 	.x2apic_available	= vmware_legacy_x2apic_available,
 };

arch/x86/kernel/process_64.c

···
 		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-#ifdef CONFIG_XEN
+#ifdef CONFIG_XEN_PV
 	/*
 	 * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
 	 * current_pt_regs()->flags may not match the current task's

arch/x86/pci/xen.c

···
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI

arch/x86/xen/Kconfig

···
 	bool "Xen guest support"
 	depends on PARAVIRT
 	select PARAVIRT_CLOCK
-	select XEN_HAVE_PVMMU
-	select XEN_HAVE_VPMU
 	depends on X86_64 || (X86_32 && X86_PAE)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
···
 	  kernel to boot in a paravirtualized environment under the
 	  Xen hypervisor.
 
-config XEN_DOM0
+config XEN_PV
+	bool "Xen PV guest support"
+	default y
+	depends on XEN
+	select XEN_HAVE_PVMMU
+	select XEN_HAVE_VPMU
+	help
+	  Support running as a Xen PV guest.
+
+config XEN_PV_SMP
 	def_bool y
-	depends on XEN && PCI_XEN && SWIOTLB_XEN
+	depends on XEN_PV && SMP
+
+config XEN_DOM0
+	bool "Xen PV Dom0 support"
+	default y
+	depends on XEN_PV && PCI_XEN && SWIOTLB_XEN
 	depends on X86_IO_APIC && ACPI && PCI
+	help
+	  Support running as a Xen PV Dom0 guest.
 
 config XEN_PVHVM
-	def_bool y
+	bool "Xen PVHVM guest support"
+	default y
 	depends on XEN && PCI && X86_LOCAL_APIC
+	help
+	  Support running as a Xen PVHVM guest.
+
+config XEN_PVHVM_SMP
+	def_bool y
+	depends on XEN_PVHVM && SMP
 
 config XEN_512GB
 	bool "Limit Xen pv-domain memory to 512GB"
-	depends on XEN && X86_64
+	depends on XEN_PV && X86_64
 	default y
 	help
 	  Limit paravirtualized user domains to 512GB of RAM.

arch/x86/xen/Makefile

···
 
 # Make sure early boot has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_enlighten.o		:= $(nostackp)
-CFLAGS_mmu.o			:= $(nostackp)
+CFLAGS_enlighten_pv.o		:= $(nostackp)
+CFLAGS_mmu_pv.o		:= $(nostackp)
 
-obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
+obj-y		:= enlighten.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
-			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o apic.o pmu.o
+			grant-table.o suspend.o platform-pci-unplug.o
+
+obj-$(CONFIG_XEN_PVHVM)		+= enlighten_hvm.o mmu_hvm.o suspend_hvm.o
+obj-$(CONFIG_XEN_PV)			+= setup.o apic.o pmu.o suspend_pv.o \
+						p2m.o enlighten_pv.o mmu_pv.o
+obj-$(CONFIG_XEN_PVH)			+= enlighten_pvh.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_XEN_PV_SMP)  	+= smp_pv.o
+obj-$(CONFIG_XEN_PVHVM_SMP)  	+= smp_hvm.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_XEN_DOM0)		+= vga.o

arch/x86/xen/efi.c

···
 	.update_capsule           = xen_efi_update_capsule,
 	.query_capsule_caps       = xen_efi_query_capsule_caps,
 	.get_next_high_mono_count = xen_efi_get_next_high_mono_count,
-	.reset_system             = NULL, /* Functionality provided by Xen. */
+	.reset_system             = xen_efi_reset_system,
 	.set_virtual_address_map  = NULL, /* Not used under Xen. */
 	.flags			  = 0     /* Initialized later. */
 };

arch/x86/xen/enlighten.c

···
-/*
- * Core of Xen paravirt_ops implementation.
- *
- * This file contains the xen_paravirt_ops structure itself, and the
- * implementations for:
- * - privileged instructions
- * - interrupt flags
- * - segment operations
- * - booting and setup
- *
- * Jeremy Fitzhardinge <[e-mail]>, XenSource Inc, 2007
- */
-
 #include <linux/cpu.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/preempt.h>
-#include <linux/hardirq.h>
-#include <linux/percpu.h>
-#include <linux/delay.h>
-#include <linux/start_kernel.h>
-#include <linux/sched.h>
-#include <linux/kprobes.h>
-#include <linux/bootmem.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/page-flags.h>
-#include <linux/highmem.h>
-#include <linux/console.h>
-#include <linux/pci.h>
-#include <linux/gfp.h>
-#include <linux/memblock.h>
-#include <linux/edd.h>
-#include <linux/frame.h>
-
 #include <linux/kexec.h>
 
-#include <xen/xen.h>
-#include <xen/events.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-#include <xen/interface/physdev.h>
-#include <xen/interface/vcpu.h>
-#include <xen/interface/memory.h>
-#include <xen/interface/nmi.h>
-#include <xen/interface/xen-mca.h>
-#include <xen/interface/hvm/start_info.h>
 #include <xen/features.h>
 #include <xen/page.h>
-#include <xen/hvm.h>
-#include <xen/hvc-console.h>
-#include <xen/acpi.h>
 
-#include <asm/paravirt.h>
-#include <asm/apic.h>
-#include <asm/page.h>
-#include <asm/xen/pci.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
-#include <asm/xen/cpuid.h>
-#include <asm/fixmap.h>
-#include <asm/processor.h>
-#include <asm/proto.h>
-#include <asm/msr-index.h>
-#include <asm/traps.h>
-#include <asm/setup.h>
-#include <asm/desc.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <asm/reboot.h>
-#include <asm/stackprotector.h>
-#include <asm/hypervisor.h>
-#include <asm/mach_traps.h>
-#include <asm/mwait.h>
-#include <asm/pci_x86.h>
 #include <asm/cpu.h>
 #include <asm/e820/api.h> 
 
-#ifdef CONFIG_ACPI
-#include <linux/acpi.h>
-#include <asm/acpi.h>
-#include <acpi/pdc_intel.h>
-#include <acpi/processor.h>
-#include <xen/interface/platform.h>
-#endif
-
 #include "xen-ops.h"
-#include "mmu.h"
 #include "smp.h"
-#include "multicalls.h"
 #include "pmu.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
···
 
 struct shared_info xen_dummy_shared_info;
 
-void *xen_initial_gdt;
-
-RESERVE_BRK(shared_info_page_brk, PAGE_SIZE);
-
-static int xen_cpu_up_prepare(unsigned int cpu);
-static int xen_cpu_up_online(unsigned int cpu);
-static int xen_cpu_dead(unsigned int cpu);
+__read_mostly int xen_have_vector_callback;
+EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
 /*
  * Point at some empty memory to start with. We map the real shared_info
···
  *
  * 0: not available, 1: available
  */
-static int have_vcpu_info_placement = 1;
+int xen_have_vcpu_info_placement = 1;
 
-struct tls_descs {
-	struct desc_struct desc[3];
-};
+static int xen_cpu_up_online(unsigned int cpu)
+{
+	xen_init_lock_cpu(cpu);
+	return 0;
+}
 
-/*
- * Updating the 3 TLS descriptors in the GDT on every task switch is
- * surprisingly expensive so we avoid updating them if they haven't
- * changed.  Since Xen writes different descriptors than the one
- * passed in the update_descriptor hypercall we keep shadow copies to
- * compare against.
- */
-static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
+int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int),
+		    int (*cpu_dead_cb)(unsigned int))
+{
+	int rc;
 
-#ifdef CONFIG_XEN_PVH
-/*
- * PVH variables.
- *
- * xen_pvh and pvh_bootparams need to live in data segment since they
- * are used after startup_{32|64}, which clear .bss, are invoked.
- */
-bool xen_pvh __attribute__((section(".data"))) = 0;
-struct boot_params pvh_bootparams __attribute__((section(".data")));
+	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
+				       "x86/xen/hvm_guest:prepare",
+				       cpu_up_prepare_cb, cpu_dead_cb);
+	if (rc >= 0) {
+		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					       "x86/xen/hvm_guest:online",
+					       xen_cpu_up_online, NULL);
+		if (rc < 0)
+			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
+	}
 
-struct hvm_start_info pvh_start_info;
-unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
-#endif
+	return rc >= 0 ? 0 : rc;
+}
 
 static void clamp_max_cpus(void)
 {
···
 		per_cpu(xen_vcpu, cpu) =
 			&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
 
-	if (!have_vcpu_info_placement) {
+	if (!xen_have_vcpu_info_placement) {
 		if (cpu >= MAX_VIRT_CPUS)
 			clamp_max_cpus();
 		return;
···
 
 	if (err) {
 		printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
-		have_vcpu_info_placement = 0;
+		xen_have_vcpu_info_placement = 0;
 		clamp_max_cpus();
 	} else {
 		/* This cpu is using the registered vcpu info, even if
···
 	}
 }
 
-/*
- * On restore, set the vcpu placement up again.
- * If it fails, then we're in a bad state, since
- * we can't back out from using it...
- */
-void xen_vcpu_restore(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		bool other_cpu = (cpu != smp_processor_id());
-		bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu),
-						NULL);
-
-		if (other_cpu && is_up &&
-		    HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
-			BUG();
-
-		xen_setup_runstate_info(cpu);
-
-		if (have_vcpu_info_placement)
-			xen_vcpu_setup(cpu);
-
-		if (other_cpu && is_up &&
-		    HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
-			BUG();
-	}
-}
-
-static void __init xen_banner(void)
-{
-	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	struct xen_extraversion extra;
-	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
-
-	pr_info("Booting paravirtualized kernel %son %s\n",
-		xen_feature(XENFEAT_auto_translated_physmap) ?
-			"with PVH extensions " : "", pv_info.name);
-	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
-	       version >> 16, version & 0xffff, extra.extraversion,
-	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
-}
-/* Check if running on Xen version (major, minor) or later */
-bool
-xen_running_on_version_or_later(unsigned int major, unsigned int minor)
-{
-	unsigned int version;
-
-	if (!xen_domain())
-		return false;
-
-	version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
-		((version >> 16) > major))
-		return true;
-	return false;
-}
-
-#define CPUID_THERM_POWER_LEAF 6
-#define APERFMPERF_PRESENT 0
-
-static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
-static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
-
-static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask;
-static __read_mostly unsigned int cpuid_leaf5_ecx_val;
-static __read_mostly unsigned int cpuid_leaf5_edx_val;
-
-static void xen_cpuid(unsigned int *ax, unsigned int *bx,
-		      unsigned int *cx, unsigned int *dx)
-{
-	unsigned maskebx = ~0;
-	unsigned maskecx = ~0;
-	unsigned maskedx = ~0;
-	unsigned setecx = 0;
-	/*
-	 * Mask out inconvenient features, to try and disable as many
-	 * unsupported kernel subsystems as possible.
-	 */
-	switch (*ax) {
-	case 1:
-		maskecx = cpuid_leaf1_ecx_mask;
-		setecx = cpuid_leaf1_ecx_set_mask;
-		maskedx = cpuid_leaf1_edx_mask;
-		break;
-
-	case CPUID_MWAIT_LEAF:
-		/* Synthesize the values.. */
-		*ax = 0;
-		*bx = 0;
-		*cx = cpuid_leaf5_ecx_val;
-		*dx = cpuid_leaf5_edx_val;
-		return;
-
-	case CPUID_THERM_POWER_LEAF:
-		/* Disabling APERFMPERF for kernel usage */
-		maskecx = ~(1 << APERFMPERF_PRESENT);
-		break;
-
-	case 0xb:
-		/* Suppress extended topology stuff */
-		maskebx = 0;
-		break;
-	}
-
-	asm(XEN_EMULATE_PREFIX "cpuid"
-		: "=a" (*ax),
-		  "=b" (*bx),
-		  "=c" (*cx),
-		  "=d" (*dx)
-		: "0" (*ax), "2" (*cx));
-
-	*bx &= maskebx;
-	*cx &= maskecx;
-	*cx |= setecx;
-	*dx &= maskedx;
-}
-STACK_FRAME_NON_STANDARD(xen_cpuid); /* XEN_EMULATE_PREFIX */
-
-static bool __init xen_check_mwait(void)
-{
-#ifdef CONFIG_ACPI
-	struct xen_platform_op op = {
-		.cmd			= XENPF_set_processor_pminfo,
-		.u.set_pminfo.id	= -1,
-		.u.set_pminfo.type	= XEN_PM_PDC,
-	};
-	uint32_t buf[3];
-	unsigned int ax, bx, cx, dx;
-	unsigned int mwait_mask;
-
-	/* We need to determine whether it is OK to expose the MWAIT
-	 * capability to the kernel to harvest deeper than C3 states from ACPI
-	 * _CST using the processor_harvest_xen.c module. For this to work, we
-	 * need to gather the MWAIT_LEAF values (which the cstate.c code
-	 * checks against). The hypervisor won't expose the MWAIT flag because
-	 * it would break backwards compatibility; so we will find out directly
-	 * from the hardware and hypercall.
-	 */
-	if (!xen_initial_domain())
-		return false;
-
-	/*
-	 * When running under platform earlier than Xen4.2, do not expose
-	 * mwait, to avoid the risk of loading native acpi pad driver
-	 */
-	if (!xen_running_on_version_or_later(4, 2))
-		return false;
-
-	ax = 1;
-	cx = 0;
-
-	native_cpuid(&ax, &bx, &cx, &dx);
-
-	mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
-		     (1 << (X86_FEATURE_MWAIT % 32));
-
-	if ((cx & mwait_mask) != mwait_mask)
-		return false;
-
-	/* We need to emulate the MWAIT_LEAF and for that we need both
-	 * ecx and edx. The hypercall provides only partial information.
-	 */
-
-	ax = CPUID_MWAIT_LEAF;
-	bx = 0;
-	cx = 0;
-	dx = 0;
-
-	native_cpuid(&ax, &bx, &cx, &dx);
-
-	/* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
-	 * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
-	 */
-	buf[0] = ACPI_PDC_REVISION_ID;
-	buf[1] = 1;
-	buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
-
-	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
-
-	if ((HYPERVISOR_platform_op(&op) == 0) &&
-	    (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
-		cpuid_leaf5_ecx_val = cx;
-		cpuid_leaf5_edx_val = dx;
-	}
-	return true;
-#else
-	return false;
-#endif
-}
-static void __init xen_init_cpuid_mask(void)
-{
-	unsigned int ax, bx, cx, dx;
-	unsigned int xsave_mask;
-
-	cpuid_leaf1_edx_mask =
-		~((1 << X86_FEATURE_MTRR) |  /* disable MTRR */
-		  (1 << X86_FEATURE_ACC));   /* thermal monitoring */
-
-	if (!xen_initial_domain())
-		cpuid_leaf1_edx_mask &=
-			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */
-
-	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
-
-	ax = 1;
-	cx = 0;
-	cpuid(1, &ax, &bx, &cx, &dx);
-
-	xsave_mask =
-		(1 << (X86_FEATURE_XSAVE % 32)) |
-		(1 << (X86_FEATURE_OSXSAVE % 32));
-
-	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
-	if ((cx & xsave_mask) != xsave_mask)
-		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
-	if (xen_check_mwait())
-		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
-}
-
-static void xen_set_debugreg(int reg, unsigned long val)
-{
-	HYPERVISOR_set_debugreg(reg, val);
-}
-
-static unsigned long xen_get_debugreg(int reg)
-{
-	return HYPERVISOR_get_debugreg(reg);
-}
-
-static void xen_end_context_switch(struct task_struct *next)
-{
-	xen_mc_flush();
-	paravirt_end_context_switch(next);
-}
-
-static unsigned long xen_store_tr(void)
-{
-	return 0;
-}
-
-/*
- * Set the page permissions for a particular virtual address.  If the
- * address is a vmalloc mapping (or other non-linear mapping), then
- * find the linear mapping of the page and also set its protections to
- * match.
- */
-static void set_aliased_prot(void *v, pgprot_t prot)
-{
-	int level;
-	pte_t *ptep;
-	pte_t pte;
-	unsigned long pfn;
-	struct page *page;
-	unsigned char dummy;
-
-	ptep = lookup_address((unsigned long)v, &level);
-	BUG_ON(ptep == NULL);
-
-	pfn = pte_pfn(*ptep);
-	page = pfn_to_page(pfn);
-
-	pte = pfn_pte(pfn, prot);
-
-	/*
-	 * Careful: update_va_mapping() will fail if the virtual address
-	 * we're poking isn't populated in the page tables.  We don't
-	 * need to worry about the direct map (that's always in the page
-	 * tables), but we need to be careful about vmap space.  In
-	 * particular, the top level page table can lazily propagate
-	 * entries between processes, so if we've switched mms since we
-	 * vmapped the target in the first place, we might not have the
-	 * top-level page table entry populated.
-	 *
-	 * We disable preemption because we want the same mm active when
-	 * we probe the target and when we issue the hypercall.  We'll
-	 * have the same nominal mm, but if we're a kernel thread, lazy
-	 * mm dropping could change our pgd.
-	 *
-	 * Out of an abundance of caution, this uses __get_user() to fault
-	 * in the target address just in case there's some obscure case
-	 * in which the target address isn't readable.
-	 */
-
-	preempt_disable();
-
-	probe_kernel_read(&dummy, v, 1);
-
-	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
-		BUG();
-
-	if (!PageHighMem(page)) {
-		void *av = __va(PFN_PHYS(pfn));
-
-		if (av != v)
-			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
-				BUG();
-	} else
-		kmap_flush_unused();
-
-	preempt_enable();
-}
-
-static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
-{
-	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
-	int i;
-
-	/*
-	 * We need to mark the all aliases of the LDT pages RO.  We
-	 * don't need to call vm_flush_aliases(), though, since that's
-	 * only responsible for flushing aliases out the TLBs, not the
-	 * page tables, and Xen will flush the TLB for us if needed.
-	 *
-	 * To avoid confusing future readers: none of this is necessary
-	 * to load the LDT.  The hypervisor only checks this when the
-	 * LDT is faulted in due to subsequent descriptor access.
-	 */
-
-	for(i = 0; i < entries; i += entries_per_page)
-		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
-}
-
-static void xen_free_ldt(struct desc_struct *ldt, unsigned entries)
-{
-	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
-	int i;
-
-	for(i = 0; i < entries; i += entries_per_page)
-		set_aliased_prot(ldt + i, PAGE_KERNEL);
-}
-
-static void xen_set_ldt(const void *addr, unsigned entries)
-{
-	struct mmuext_op *op;
-	struct multicall_space mcs = xen_mc_entry(sizeof(*op));
-
-	trace_xen_cpu_set_ldt(addr, entries);
-
-	op = mcs.args;
-	op->cmd = MMUEXT_SET_LDT;
-	op->arg1.linear_addr = (unsigned long)addr;
-	op->arg2.nr_ents = entries;
-
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
-}
-
-static void xen_load_gdt(const struct desc_ptr *dtr)
-{
-	unsigned long va = dtr->address;
-	unsigned int size = dtr->size + 1;
-	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
-	unsigned long frames[pages];
-	int f;
-
-	/*
-	 * A GDT can be up to 64k in size, which corresponds to 8192
-	 * 8-byte entries, or 16 4k pages..
-	 */
-
-	BUG_ON(size > 65536);
-	BUG_ON(va & ~PAGE_MASK);
-
-	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
-		int level;
-		pte_t *ptep;
-		unsigned long pfn, mfn;
-		void *virt;
-
-		/*
-		 * The GDT is per-cpu and is in the percpu data area.
-		 * That can be virtually mapped, so we need to do a
-		 * page-walk to get the underlying MFN for the
-		 * hypercall.  The page can also be in the kernel's
-		 * linear range, so we need to RO that mapping too.
-		 */
-		ptep = lookup_address(va, &level);
-		BUG_ON(ptep == NULL);
-
-		pfn = pte_pfn(*ptep);
-		mfn = pfn_to_mfn(pfn);
-		virt = __va(PFN_PHYS(pfn));
-
-		frames[f] = mfn;
-
-		make_lowmem_page_readonly((void *)va);
-		make_lowmem_page_readonly(virt);
-	}
-
-	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
-		BUG();
-}
-
-/*
- * load_gdt for early boot, when the gdt is only mapped once
- */
-static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
-{
-	unsigned long va = dtr->address;
-	unsigned int size = dtr->size + 1;
-	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
-	unsigned long frames[pages];
-	int f;
-
-	/*
-	 * A GDT can be up to 64k in size, which corresponds to 8192
-	 * 8-byte entries, or 16 4k pages..
-	 */
-
-	BUG_ON(size > 65536);
-	BUG_ON(va & ~PAGE_MASK);
-
-	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
-		pte_t pte;
-		unsigned long pfn, mfn;
-
-		pfn = virt_to_pfn(va);
-		mfn = pfn_to_mfn(pfn);
-
-		pte = pfn_pte(pfn, PAGE_KERNEL_RO);
-
-		if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
-			BUG();
-
-		frames[f] = mfn;
-	}
-
-	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
-		BUG();
-}
-
-static inline bool desc_equal(const struct desc_struct *d1,
-			      const struct desc_struct *d2)
-{
-	return d1->a == d2->a && d1->b == d2->b;
-}
-
-static void load_TLS_descriptor(struct thread_struct *t,
-				unsigned int cpu, unsigned int i)
-{
-	struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i];
-	struct desc_struct *gdt;
-	xmaddr_t maddr;
-	struct multicall_space mc;
-
-	if (desc_equal(shadow, &t->tls_array[i]))
-		return;
-
-	*shadow = t->tls_array[i];
-
-	gdt = get_cpu_gdt_rw(cpu);
-	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
-	mc = __xen_mc_entry(0);
-
-	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
-}
-
-static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	/*
-	 * XXX sleazy hack: If we're being called in a lazy-cpu zone
-	 * and lazy gs handling is enabled, it means we're in a
-	 * context switch, and %gs has just been saved.  This means we
-	 * can zero it out to prevent faults on exit from the
-	 * hypervisor if the next process has no %gs.  Either way, it
-	 * has been saved, and the new value will get loaded properly.
-	 * This will go away as soon as Xen has been modified to not
-	 * save/restore %gs for normal hypercalls.
-	 *
-	 * On x86_64, this hack is not used for %gs, because gs points
-	 * to KERNEL_GS_BASE (and uses it for PDA references), so we
-	 * must not zero %gs on x86_64
-	 *
-	 * For x86_64, we need to zero %fs, otherwise we may get an
-	 * exception between the new %fs descriptor being loaded and
-	 * %fs being effectively cleared at __switch_to().
-	 */
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-#ifdef CONFIG_X86_32
-		lazy_load_gs(0);
-#else
-		loadsegment(fs, 0);
-#endif
-	}
-
-	xen_mc_batch();
-
-	load_TLS_descriptor(t, cpu, 0);
-	load_TLS_descriptor(t, cpu, 1);
-	load_TLS_descriptor(t, cpu, 2);
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
-}
-
-#ifdef CONFIG_X86_64
-static void xen_load_gs_index(unsigned int idx)
-{
-	if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
-		BUG();
-}
-#endif
-
-static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
-				const void *ptr)
-{
-	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
-	u64 entry = *(u64 *)ptr;
-
-	trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
-
-	preempt_disable();
-
-	xen_mc_flush();
-	if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry))
-		BUG();
-
-	preempt_enable();
-}
-
-static int cvt_gate_to_trap(int vector, const gate_desc *val,
-			    struct trap_info *info)
-{
-	unsigned long addr;
-
-	if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
-		return 0;
-
-	info->vector = vector;
-
-	addr = gate_offset(*val);
-#ifdef CONFIG_X86_64
-	/*
-	 * Look for known traps using IST, and substitute them
-	 * appropriately.  The debugger ones are the only ones we care
-	 * about.  Xen will handle faults like double_fault,
-	 * so we should never see them.  Warn if
-	 * there's an unexpected IST-using fault handler.
-	 */
-	if (addr == (unsigned long)debug)
-		addr = (unsigned long)xen_debug;
-	else if (addr == (unsigned long)int3)
-		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) {
-		/* Don't need to handle these */
-		return 0;
-#ifdef CONFIG_X86_MCE
-	} else if (addr == (unsigned long)machine_check) {
-		/*
-		 * when xen hypervisor inject vMCE to guest,
-		 * use native mce handler to handle it
-		 */
-		;
-#endif
-	} 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;
-	}
-#endif	/* CONFIG_X86_64 */
-	info->address = addr;
-
-	info->cs = gate_segment(*val);
-	info->flags = val->dpl;
-	/* interrupt gates clear IF */
-	if (val->type == GATE_INTERRUPT)
-		info->flags |= 1 << 2;
-
-	return 1;
-}
-
-/* Locations of each CPU's IDT */
-static DEFINE_PER_CPU(struct desc_ptr, idt_desc);
-
-/* Set an IDT entry.  If the entry is part of the current IDT, then
-   also update Xen. */
-static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
-{
-	unsigned long p = (unsigned long)&dt[entrynum];
-	unsigned long start, end;
-
-	trace_xen_cpu_write_idt_entry(dt, entrynum, g);
-
-	preempt_disable();
-
-	start = __this_cpu_read(idt_desc.address);
-	end = start + __this_cpu_read(idt_desc.size) + 1;
-
-	xen_mc_flush();
-
-	native_write_idt_entry(dt, entrynum, g);
-
-	if (p >= start && (p + 8) <= end) {
-		struct trap_info info[2];
-
-		info[1].address = 0;
-
-		if (cvt_gate_to_trap(entrynum, g, &info[0]))
-			if (HYPERVISOR_set_trap_table(info))
-				BUG();
-	}
-
-	preempt_enable();
-}
-
-static void xen_convert_trap_info(const struct desc_ptr *desc,
-				  struct trap_info *traps)
-{
-	unsigned in, out, count;
-
-	count = (desc->size+1) / sizeof(gate_desc);
-	BUG_ON(count > 256);
-
-	for (in = out = 0; in < count; in++) {
-		gate_desc *entry = (gate_desc*)(desc->address) + in;
-
-		if (cvt_gate_to_trap(in, entry, &traps[out]))
-			out++;
-	}
-	traps[out].address = 0;
-}
-
-void xen_copy_trap_info(struct trap_info *traps)
-{
-	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
-
-	xen_convert_trap_info(desc, traps);
-}
-
-/* Load a new IDT into Xen.  In principle this can be per-CPU, so we
-   hold a spinlock to protect the static traps[] array (static because
-   it avoids allocation, and saves stack space). */
-static void xen_load_idt(const struct desc_ptr *desc)
-{
-	static DEFINE_SPINLOCK(lock);
-	static struct trap_info traps[257];
-
-	trace_xen_cpu_load_idt(desc);
-
-	spin_lock(&lock);
-
-	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
-
-	xen_convert_trap_info(desc, traps);
-
-	xen_mc_flush();
-	if (HYPERVISOR_set_trap_table(traps))
-		BUG();
-
-	spin_unlock(&lock);
-}
-
-/* Write a GDT descriptor entry.  Ignore LDT descriptors, since
-   they're handled differently. */
-static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
-				const void *desc, int type)
-{
-	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
-
-	preempt_disable();
-
-	switch (type) {
-	case DESC_LDT:
-	case DESC_TSS:
-		/* ignore */
-		break;
-
-	default: {
-		xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]);
-
-		xen_mc_flush();
-		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
-			BUG();
-	}
-
-	}
-
-	preempt_enable();
-}
-
-/*
- * Version of write_gdt_entry for use at early boot-time needed to
- * update an entry as simply as possible.
- */
-static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
-					    const void *desc, int type)
-{
-	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
-
-	switch (type) {
-	case DESC_LDT:
-	case DESC_TSS:
-		/* ignore */
-		break;
-
-	default: {
-		xmaddr_t maddr = virt_to_machine(&dt[entry]);
-
-		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
-			dt[entry] = *(struct desc_struct *)desc;
-	}
-
-	}
-}
-
-static void xen_load_sp0(struct tss_struct *tss,
-			 struct thread_struct *thread)
-{
-	struct multicall_space mcs;
-
-	mcs = xen_mc_entry(0);
-	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	tss->x86_tss.sp0 = thread->sp0;
-}
-
-void xen_set_iopl_mask(unsigned mask)
-{
-	struct physdev_set_iopl set_iopl;
-
-	/* Force the change at ring 0. */
-	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
-	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-}
-
-static void xen_io_delay(void)
-{
-}
-
-static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
-
-static unsigned long xen_read_cr0(void)
-{
-	unsigned long cr0 = this_cpu_read(xen_cr0_value);
-
-	if (unlikely(cr0 == 0)) {
-		cr0 = native_read_cr0();
-		this_cpu_write(xen_cr0_value, cr0);
-	}
-
-	return cr0;
-}
-
-static void xen_write_cr0(unsigned long cr0)
-{
-	struct multicall_space mcs;
-
-	this_cpu_write(xen_cr0_value, cr0);
-
-	/* Only pay attention to cr0.TS; everything else is
-	   ignored. */
-	mcs = xen_mc_entry(0);
-
-	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
-}
-
-static void xen_write_cr4(unsigned long cr4)
-{
-	cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE);
-
-	native_write_cr4(cr4);
-}
-#ifdef CONFIG_X86_64
-static inline unsigned long xen_read_cr8(void)
-{
-	return 0;
-}
-static inline void xen_write_cr8(unsigned long val)
-{
-	BUG_ON(val);
-}
-#endif
-
-static u64 xen_read_msr_safe(unsigned int msr, int *err)
-{
-	u64 val;
-
-	if (pmu_msr_read(msr, &val, err))
-		return val;
-
-	val = native_read_msr_safe(msr, err);
-	switch (msr) {
-	case MSR_IA32_APICBASE:
-#ifdef CONFIG_X86_X2APIC
-		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
-#endif
-			val &= ~X2APIC_ENABLE;
-		break;
-	}
-	return val;
-}
-
-static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
-{
-	int ret;
-
-	ret = 0;
-
-	switch (msr) {
-#ifdef CONFIG_X86_64
-		unsigned which;
-		u64 base;
-
-	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
-	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
-	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
-
-	set:
-		base = ((u64)high << 32) | low;
-		if (HYPERVISOR_set_segment_base(which, base) != 0)
-			ret = -EIO;
-		break;
-#endif
-
-	case MSR_STAR:
-	case MSR_CSTAR:
-	case MSR_LSTAR:
-	case MSR_SYSCALL_MASK:
-	case MSR_IA32_SYSENTER_CS:
-	case MSR_IA32_SYSENTER_ESP:
-	case MSR_IA32_SYSENTER_EIP:
-		/* Fast syscall setup is all done in hypercalls, so
-		   these are all ignored.  Stub them out here to stop
-		   Xen console noise. */
-		break;
-
-	default:
-		if (!pmu_msr_write(msr, low, high, &ret))
-			ret = native_write_msr_safe(msr, low, high);
-	}
-
-	return ret;
-}
-
-static u64 xen_read_msr(unsigned int msr)
-{
-	/*
-	 * This will silently swallow a #GP from RDMSR.  It may be worth
-	 * changing that.
-	 */
-	int err;
-
-	return xen_read_msr_safe(msr, &err);
-}
-
-static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
-{
-	/*
-	 * This will silently swallow a #GP from WRMSR.  It may be worth
-	 * changing that.
-	 */
-	xen_write_msr_safe(msr, low, high);
-}
-
-void xen_setup_shared_info(void)
-{
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		set_fixmap(FIX_PARAVIRT_BOOTMAP,
-			   xen_start_info->shared_info);
-
-		HYPERVISOR_shared_info =
-			(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-	} else
-		HYPERVISOR_shared_info =
-			(struct shared_info *)__va(xen_start_info->shared_info);
-
-#ifndef CONFIG_SMP
-	/* In UP this is as good a place as any to set up shared info */
-	xen_setup_vcpu_info_placement();
-#endif
-
-	xen_setup_mfn_list_list();
-}
-
-/* This is called once we have the cpu_possible_mask */
-void xen_setup_vcpu_info_placement(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		/* Set up direct vCPU id mapping for PV guests. */
-		per_cpu(xen_vcpu_id, cpu) = cpu;
-		xen_vcpu_setup(cpu);
-	}
-
-	/*
-	 * xen_vcpu_setup managed to place the vcpu_info within the
-	 * percpu area for all cpus, so make use of it.
-	 */
-	if (have_vcpu_info_placement) {
-		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
-		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
-		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
-		pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
-		pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
-	}
-}
-
-static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
-			  unsigned long addr, unsigned len)
-{
-	char *start, *end, *reloc;
-	unsigned ret;
-
-	start = end = reloc = NULL;
-
-#define SITE(op, x)							\
-	case PARAVIRT_PATCH(op.x):					\
-	if (have_vcpu_info_placement) {					\
-		start = (char *)xen_##x##_direct;			\
-		end = xen_##x##_direct_end;				\
-		reloc = xen_##x##_direct_reloc;				\
-	}								\
-	goto patch_site
-
-	switch (type) {
-		SITE(pv_irq_ops, irq_enable);
-		SITE(pv_irq_ops, irq_disable);
-		SITE(pv_irq_ops, save_fl);
-		SITE(pv_irq_ops, restore_fl);
-#undef SITE
-
-	patch_site:
-		if (start == NULL || (end-start) > len)
-			goto default_patch;
-
-		ret = paravirt_patch_insns(insnbuf, len, start, end);
-
-		/* Note: because reloc is assigned from something that
-		   appears to be an array, gcc assumes it's non-null,
-		   but doesn't know its relationship with start and
-		   end. */
-		if (reloc > start && reloc < end) {
-			int reloc_off = reloc - start;
-			long *relocp = (long *)(insnbuf + reloc_off);
-			long delta = start - (char *)addr;
-
-			*relocp += delta;
-		}
-		break;
-
-	default_patch:
-	default:
-		ret = paravirt_patch_default(type, clobbers, insnbuf,
-					     addr, len);
-		break;
-	}
-
-	return ret;
-}
-
-static const struct pv_info xen_info __initconst = {
-	.shared_kernel_pmd = 0,
-
-#ifdef CONFIG_X86_64
-	.extra_user_64bit_cs = FLAT_USER_CS64,
-#endif
-	.name = "Xen",
-};
-
-static const struct pv_init_ops xen_init_ops __initconst = {
-	.patch = xen_patch,
-};
-
-static const struct pv_cpu_ops xen_cpu_ops __initconst = {
-	.cpuid = xen_cpuid,
-
-	.set_debugreg = xen_set_debugreg,
-	.get_debugreg = xen_get_debugreg,
-
-	.read_cr0 = xen_read_cr0,
-	.write_cr0 = xen_write_cr0,
-
-	.read_cr4 = native_read_cr4,
-	.write_cr4 = xen_write_cr4,
-
-#ifdef CONFIG_X86_64
-	.read_cr8 = xen_read_cr8,
-	.write_cr8 = xen_write_cr8,
-#endif
-
-	.wbinvd = native_wbinvd,
-
-	.read_msr = xen_read_msr,
-	.write_msr = xen_write_msr,
-
-	.read_msr_safe = xen_read_msr_safe,
-	.write_msr_safe = xen_write_msr_safe,
-
-	.read_pmc = xen_read_pmc,
-
-	.iret = xen_iret,
-#ifdef CONFIG_X86_64
-	.usergs_sysret64 = xen_sysret64,
-#endif
-
-	.load_tr_desc = paravirt_nop,
-	.set_ldt = xen_set_ldt,
-	.load_gdt = xen_load_gdt,
-	.load_idt = xen_load_idt,
-	.load_tls = xen_load_tls,
-#ifdef CONFIG_X86_64
-	.load_gs_index = xen_load_gs_index,
-#endif
-
-	.alloc_ldt = xen_alloc_ldt,
-	.free_ldt = xen_free_ldt,
-
-	.store_idt = native_store_idt,
-	.store_tr = xen_store_tr,
-
-	.write_ldt_entry = xen_write_ldt_entry,
-	.write_gdt_entry = xen_write_gdt_entry,
-	.write_idt_entry = xen_write_idt_entry,
-	.load_sp0 = xen_load_sp0,
-
-	.set_iopl_mask = xen_set_iopl_mask,
-	.io_delay = xen_io_delay,
-
-	/* Xen takes care of %gs when switching to usermode for us */
-	.swapgs = paravirt_nop,
-
-	.start_context_switch = paravirt_start_context_switch,
-	.end_context_switch = xen_end_context_switch,
-};
-
-static void xen_reboot(int reason)
+void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
 	int cpu;
···
 		BUG();
 }
 
-static void xen_restart(char *msg)
+void xen_emergency_restart(void)
 {
 	xen_reboot(SHUTDOWN_reboot);
-}
-
-static void xen_emergency_restart(void)
-{
-	xen_reboot(SHUTDOWN_reboot);
-}
-
-static void xen_machine_halt(void)
-{
-	xen_reboot(SHUTDOWN_poweroff);
-}
-
-static void xen_machine_power_off(void)
-{
-	if (pm_power_off)
-		pm_power_off();
-	xen_reboot(SHUTDOWN_poweroff);
-}
-
-static void xen_crash_shutdown(struct pt_regs *regs)
-{
-	xen_reboot(SHUTDOWN_crash);
 }
 
 static int
···
 }
 
 static struct notifier_block xen_panic_block = {
-	.notifier_call= xen_panic_event,
+	.notifier_call = xen_panic_event,
 	.priority = INT_MIN
 };
 
···
 	return 0;
 }
 
-static const struct machine_ops xen_machine_ops __initconst = {
-	.restart = xen_restart,
-	.halt = xen_machine_halt,
-	.power_off = xen_machine_power_off,
-	.shutdown = xen_machine_halt,
-	.crash_shutdown = xen_crash_shutdown,
-	.emergency_restart = xen_emergency_restart,
-};
-
-static unsigned char xen_get_nmi_reason(void)
-{
-	unsigned char reason = 0;
-
-	/* Construct a value which looks like it came from port 0x61. */
-	if (test_bit(_XEN_NMIREASON_io_error,
-		     &HYPERVISOR_shared_info->arch.nmi_reason))
-		reason |= NMI_REASON_IOCHK;
-	if (test_bit(_XEN_NMIREASON_pci_serr,
-		     &HYPERVISOR_shared_info->arch.nmi_reason))
-		reason |= NMI_REASON_SERR;
-
-	return reason;
-}
-
-static void __init xen_boot_params_init_edd(void)
-{
-#if IS_ENABLED(CONFIG_EDD)
-	struct xen_platform_op op;
-	struct edd_info *edd_info;
-	u32 *mbr_signature;
-	unsigned nr;
-	int ret;
-
-	edd_info = boot_params.eddbuf;
-	mbr_signature = boot_params.edd_mbr_sig_buffer;
-
-	op.cmd = XENPF_firmware_info;
-
-	op.u.firmware_info.type = XEN_FW_DISK_INFO;
-	for (nr = 0; nr < EDDMAXNR; nr++) {
-		struct edd_info *info = edd_info + nr;
-
-		op.u.firmware_info.index = nr;
-		info->params.length = sizeof(info->params);
-		set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
-				     &info->params);
-		ret = HYPERVISOR_platform_op(&op);
-		if (ret)
-			break;
-
-#define C(x) info->x = op.u.firmware_info.u.disk_info.x
-		C(device);
-		C(version);
-		C(interface_support);
-		C(legacy_max_cylinder);
-		C(legacy_max_head);
-		C(legacy_sectors_per_track);
-#undef C
-	}
-	boot_params.eddbuf_entries = nr;
-
-	op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
-	for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
-		op.u.firmware_info.index = nr;
-		ret = HYPERVISOR_platform_op(&op);
-		if (ret)
-			break;
-		mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
-	}
-	boot_params.edd_mbr_sig_buf_entries = nr;
-#endif
-}
-
-/*
- * Set up the GDT and segment registers for -fstack-protector.  Until
- * we do this, we have to be careful not to call any stack-protected
- * function, which is most of the kernel.
- */
-static void xen_setup_gdt(int cpu)
-{
-	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
-	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
-
-	setup_stack_canary_segment(0);
-	switch_to_new_gdt(0);
-
-	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry;
-	pv_cpu_ops.load_gdt = xen_load_gdt;
-}
-
-static void __init xen_dom0_set_legacy_features(void)
-{
-	x86_platform.legacy.rtc = 1;
-}
-
-static int xen_cpuhp_setup(void)
-{
-	int rc;
-
-	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "x86/xen/hvm_guest:prepare",
-				       xen_cpu_up_prepare, xen_cpu_dead);
-	if (rc >= 0) {
-		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "x86/xen/hvm_guest:online",
-					       xen_cpu_up_online, NULL);
-		if (rc < 0)
-			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
-	}
-
-	return rc >= 0 ? 0 : rc;
-}
-
-/* First C function to be called on Xen boot */
-asmlinkage __visible void __init xen_start_kernel(void)
-{
-	struct physdev_set_iopl set_iopl;
-	unsigned long initrd_start = 0;
-	int rc;
-
-	if (!xen_start_info)
-		return;
-
-	xen_domain_type = XEN_PV_DOMAIN;
-
-	xen_setup_features();
-
-	xen_setup_machphys_mapping();
-
-	/* Install Xen paravirt ops */
-	pv_info = xen_info;
-	pv_init_ops = xen_init_ops;
-	pv_cpu_ops = xen_cpu_ops;
-
-	x86_platform.get_nmi_reason = xen_get_nmi_reason;
-
-	x86_init.resources.memory_setup = xen_memory_setup;
-	x86_init.oem.arch_setup = xen_arch_setup;
-	x86_init.oem.banner = xen_banner;
-
-	xen_init_time_ops();
-
-	/*
-	 * Set up some pagetable state before starting to set any ptes.
-	 */
-
-	xen_init_mmu_ops();
-
-	/* Prevent unwanted bits from being set in PTEs. */
-	__supported_pte_mask &= ~_PAGE_GLOBAL;
-
-	/*
-	 * Prevent page tables from being allocated in highmem, even
-	 * if CONFIG_HIGHPTE is enabled.
-	 */
-	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
-	/* Work out if we support NX */
-	x86_configure_nx();
-
-	/* Get mfn list */
-	xen_build_dynamic_phys_to_machine();
-
-	/*
-	 * Set up kernel GDT and segment registers, mainly so that
-	 * -fstack-protector code can be executed.
-	 */
-	xen_setup_gdt(0);
-
-	xen_init_irq_ops();
-	xen_init_cpuid_mask();
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	/*
-	 * set up the basic apic ops.
-	 */
-	xen_init_apic();
-#endif
-
-	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
-		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
-		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
-	}
-
-	machine_ops = xen_machine_ops;
-
-	/*
-	 * The only reliable way to retain the initial address of the
-	 * percpu gdt_page is to remember it here, so we can go and
-	 * mark it RW later, when the initial percpu area is freed.
-	 */
-	xen_initial_gdt = &per_cpu(gdt_page, 0);
-
-	xen_smp_init();
-
-#ifdef CONFIG_ACPI_NUMA
-	/*
-	 * The pages we from Xen are not related to machine pages, so
-	 * any NUMA information the kernel tries to get from ACPI will
-	 * be meaningless.  Prevent it from trying.
-	 */
-	acpi_numa = -1;
-#endif
-	/* Don't do the full vcpu_info placement stuff until we have a
-	   possible map and a non-dummy shared_info. */
-	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
-
-	WARN_ON(xen_cpuhp_setup());
-
-	local_irq_disable();
-	early_boot_irqs_disabled = true;
-
-	xen_raw_console_write("mapping kernel into physical memory\n");
-	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
-				   xen_start_info->nr_pages);
-	xen_reserve_special_pages();
-
-	/* keep using Xen gdt for now; no urgent need to change it */
-
-#ifdef CONFIG_X86_32
-	pv_info.kernel_rpl = 1;
-	if (xen_feature(XENFEAT_supervisor_mode_kernel))
-		pv_info.kernel_rpl = 0;
-#else
-	pv_info.kernel_rpl = 0;
-#endif
-	/* set the limit of our address space */
-	xen_reserve_top();
-
-	/*
-	 * We used to do this in xen_arch_setup, but that is too late
-	 * on AMD were early_cpu_init (run before ->arch_setup()) calls
-	 * early_amd_init which pokes 0xcf8 port.
-	 */
-	set_iopl.iopl = 1;
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-	if (rc != 0)
-		xen_raw_printk("physdev_op failed %d\n", rc);
-
-#ifdef CONFIG_X86_32
-	/* set up basic CPUID stuff */
-	cpu_detect(&new_cpu_data);
-	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
-	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
-#endif
-
-	if (xen_start_info->mod_start) {
-	    if (xen_start_info->flags & SIF_MOD_START_PFN)
-		initrd_start = PFN_PHYS(xen_start_info->mod_start);
-	    else
-		initrd_start = __pa(xen_start_info->mod_start);
-	}
-
-	/* Poke various useful things into boot_params */
-	boot_params.hdr.type_of_loader = (9 << 4) | 0;
-	boot_params.hdr.ramdisk_image = initrd_start;
-	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
-	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
-	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
-
-	if (!xen_initial_domain()) {
-		add_preferred_console("xenboot", 0, NULL);
-		add_preferred_console("tty", 0, NULL);
-		add_preferred_console("hvc", 0, NULL);
-		if (pci_xen)
-			x86_init.pci.arch_init = pci_xen_init;
-	} else {
-		const struct dom0_vga_console_info *info =
-			(void *)((char *)xen_start_info +
-				 xen_start_info->console.dom0.info_off);
-		struct xen_platform_op op = {
-			.cmd = XENPF_firmware_info,
-			.interface_version = XENPF_INTERFACE_VERSION,
-			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
-		};
-
-		x86_platform.set_legacy_features =
-				xen_dom0_set_legacy_features;
-		xen_init_vga(info, xen_start_info->console.dom0.info_size);
-		xen_start_info->console.domU.mfn = 0;
-		xen_start_info->console.domU.evtchn = 0;
-
-		if (HYPERVISOR_platform_op(&op) == 0)
-			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
-
-		/* Make sure ACS will be enabled */
-		pci_request_acs();
-
-		xen_acpi_sleep_register();
-
-		/* Avoid searching for BIOS MP tables */
-		x86_init.mpparse.find_smp_config = x86_init_noop;
-		x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-
-		xen_boot_params_init_edd();
-	}
-#ifdef CONFIG_PCI
-	/* PCI BIOS service won't work from a PV guest. */
-	pci_probe &= ~PCI_PROBE_BIOS;
-#endif
-	xen_raw_console_write("about to get started...\n");
-
-	/* Let's presume PV guests always boot on vCPU with id 0. */
-	per_cpu(xen_vcpu_id, 0) = 0;
-
-	xen_setup_runstate_info(0);
-
-	xen_efi_init();
-
-	/* Start the world */
-#ifdef CONFIG_X86_32
-	i386_start_kernel();
-#else
-	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
-	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
-#endif
-}
-
-#ifdef CONFIG_XEN_PVH
-
-static void xen_pvh_arch_setup(void)
-{
-#ifdef CONFIG_ACPI
-	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
-	if (nr_ioapics == 0)
-		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
-#endif
-}
-
-static void __init init_pvh_bootparams(void)
-{
-	struct xen_memory_map memmap;
-	unsigned int i;
-	int rc;
-
-	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
-
-	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table);
-	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table);
-	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
-	if (rc) {
-		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
-		BUG();
-	}
-
-	if (memmap.nr_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) {
-		pvh_bootparams.e820_table[memmap.nr_entries].addr =
-			ISA_START_ADDRESS;
-		pvh_bootparams.e820_table[memmap.nr_entries].size =
-			ISA_END_ADDRESS - ISA_START_ADDRESS;
-		pvh_bootparams.e820_table[memmap.nr_entries].type =
-			E820_TYPE_RESERVED;
-		memmap.nr_entries++;
-	} else
-		xen_raw_printk("Warning: Can fit ISA range into e820\n");
-
-	pvh_bootparams.e820_entries = memmap.nr_entries;
-	for (i = 0; i < pvh_bootparams.e820_entries; i++)
-		e820__range_add(pvh_bootparams.e820_table[i].addr,
-				pvh_bootparams.e820_table[i].size,
-				pvh_bootparams.e820_table[i].type);
-
-	e820__update_table(e820_table);
-
-	pvh_bootparams.hdr.cmd_line_ptr =
-		pvh_start_info.cmdline_paddr;
-
-	/* The first module is always ramdisk. */
-	if (pvh_start_info.nr_modules) {
-		struct hvm_modlist_entry *modaddr =
-			__va(pvh_start_info.modlist_paddr);
-		pvh_bootparams.hdr.ramdisk_image = modaddr->paddr;
-		pvh_bootparams.hdr.ramdisk_size = modaddr->size;
-	}
-
-	/*
-	 * See Documentation/x86/boot.txt.
-	 *
-	 * Version 2.12 supports Xen entry point but we will use default x86/PC
-	 * environment (i.e. hardware_subarch 0).
-	 */
-	pvh_bootparams.hdr.version = 0x212;
-	pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
-}
-
-/*
- * This routine (and those that it might call) should not use
- * anything that lives in .bss since that segment will be cleared later.
- */
-void __init xen_prepare_pvh(void)
-{
-	u32 msr;
-	u64 pfn;
-
-	if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
-		xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
-				pvh_start_info.magic);
-		BUG();
-	}
-
-	xen_pvh = 1;
-
-	msr = cpuid_ebx(xen_cpuid_base() + 2);
-	pfn = __pa(hypercall_page);
-	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-
-	init_pvh_bootparams();
-
-	x86_init.oem.arch_setup = xen_pvh_arch_setup;
-}
-#endif
-
-void __ref xen_hvm_init_shared_info(void)
-{
-	int cpu;
-	struct xen_add_to_physmap xatp;
-	static struct shared_info *shared_info_page = 0;
-
-	if (!shared_info_page)
-		shared_info_page = (struct shared_info *)
-			extend_brk(PAGE_SIZE, PAGE_SIZE);
-	xatp.domid = DOMID_SELF;
-	xatp.idx = 0;
-	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
-	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
-		BUG();
-
-	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
-
-	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
-	 * page, we use it in the event channel upcall and in some pvclock
-	 * related functions. We don't need the vcpu_info placement
-	 * optimizations because we don't use any pv_mmu or pv_irq op on
-	 * HVM.
-	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
-	 * online but xen_hvm_init_shared_info is run at resume time too and
-	 * in that case multiple vcpus might be online. */
-	for_each_online_cpu(cpu) {
-		/* Leave it to be NULL. */
-		if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
-			continue;
-		per_cpu(xen_vcpu, cpu) =
-			&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
-	}
-}
-
-#ifdef CONFIG_XEN_PVHVM
-static void __init init_hvm_pv_info(void)
-{
-	int major, minor;
-	uint32_t eax, ebx, ecx, edx, base;
-
-	base = xen_cpuid_base();
-	eax = cpuid_eax(base + 1);
-
-	major = eax >> 16;
-	minor = eax & 0xffff;
-	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
-
-	xen_domain_type = XEN_HVM_DOMAIN;
-
-	/* PVH set up hypercall page in xen_prepare_pvh(). */
-	if (xen_pvh_domain())
-		pv_info.name = "Xen PVH";
-	else {
-		u64 pfn;
-		uint32_t msr;
-
-		pv_info.name = "Xen HVM";
-		msr = cpuid_ebx(base + 2);
-		pfn = __pa(hypercall_page);
-		wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-	}
-
-	xen_setup_features();
-
-	cpuid(base + 4, &eax, &ebx, &ecx, &edx);
-	if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
-		this_cpu_write(xen_vcpu_id, ebx);
-	else
-		this_cpu_write(xen_vcpu_id, smp_processor_id());
-}
-#endif
-
-static int xen_cpu_up_prepare(unsigned int cpu)
-{
-	int rc;
-
-	if (xen_hvm_domain()) {
-		/*
-		 * This can happen if CPU was offlined earlier and
-		 * offlining timed out in common_cpu_die().
-		 */
-		if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
-			xen_smp_intr_free(cpu);
-			xen_uninit_lock_cpu(cpu);
-		}
-
-		if (cpu_acpi_id(cpu) != U32_MAX)
-			per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
-		else
-			per_cpu(xen_vcpu_id, cpu) = cpu;
-		xen_vcpu_setup(cpu);
-	}
-
-	if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
-		xen_setup_timer(cpu);
-
-	rc = xen_smp_intr_init(cpu);
-	if (rc) {
-		WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n",
-		     cpu, rc);
-		return rc;
-	}
-	return 0;
-}
-
-static int xen_cpu_dead(unsigned int cpu)
-{
-	xen_smp_intr_free(cpu);
-
-	if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
-		xen_teardown_timer(cpu);
-
-	return 0;
-}
-
-static int xen_cpu_up_online(unsigned int cpu)
-{
-	xen_init_lock_cpu(cpu);
-	return 0;
-}
-
-#ifdef CONFIG_XEN_PVHVM
-#ifdef CONFIG_KEXEC_CORE
-static void xen_hvm_shutdown(void)
-{
-	native_machine_shutdown();
-	if (kexec_in_progress)
-		xen_reboot(SHUTDOWN_soft_reset);
-}
-
-static void xen_hvm_crash_shutdown(struct pt_regs *regs)
-{
-	native_machine_crash_shutdown(regs);
-	xen_reboot(SHUTDOWN_soft_reset);
-}
-#endif
-
-static void __init xen_hvm_guest_init(void)
-{
-	if (xen_pv_domain())
-		return;
-
-	init_hvm_pv_info();
-
-	xen_hvm_init_shared_info();
-
-	xen_panic_handler_init();
-
-	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
-
-	xen_hvm_smp_init();
-	WARN_ON(xen_cpuhp_setup());
-	xen_unplug_emulated_devices();
-	x86_init.irqs.intr_init = xen_init_IRQ;
-	xen_hvm_init_time_ops();
-	xen_hvm_init_mmu_ops();
-
-	if (xen_pvh_domain())
-		machine_ops.emergency_restart = xen_emergency_restart;
-#ifdef CONFIG_KEXEC_CORE
-	machine_ops.shutdown = xen_hvm_shutdown;
-	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
-#endif
-}
-#endif
-
-static bool xen_nopv = false;
-static __init int xen_parse_nopv(char *arg)
-{
-       xen_nopv = true;
-       return 0;
-}
-early_param("xen_nopv", xen_parse_nopv);
-
-static uint32_t __init xen_platform(void)
-{
-	if (xen_nopv)
-		return 0;
-
-	return xen_cpuid_base();
-}
-
-bool xen_hvm_need_lapic(void)
-{
-	if (xen_nopv)
-		return false;
-	if (xen_pv_domain())
-		return false;
-	if (!xen_hvm_domain())
-		return false;
-	if (xen_feature(XENFEAT_hvm_pirqs))
-		return false;
-	return true;
-}
-EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
-
-static void xen_set_cpu_features(struct cpuinfo_x86 *c)
-{
-	if (xen_pv_domain()) {
-		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
-		set_cpu_cap(c, X86_FEATURE_XENPV);
-	}
-}
-
-static void xen_pin_vcpu(int cpu)
+void xen_pin_vcpu(int cpu)
 {
 	static bool disable_pinning;
 	struct sched_pin_override pin_override;
···
 		disable_pinning = true;
 	}
 }
-
-const struct hypervisor_x86 x86_hyper_xen = {
-	.name			= "Xen",
-	.detect			= xen_platform,
-#ifdef CONFIG_XEN_PVHVM
-	.init_platform		= xen_hvm_guest_init,
-#endif
-	.x2apic_available	= xen_x2apic_para_available,
-	.set_cpu_features       = xen_set_cpu_features,
-	.pin_vcpu               = xen_pin_vcpu,
-};
-EXPORT_SYMBOL(x86_hyper_xen);
 
 #ifdef CONFIG_HOTPLUG_CPU
 void xen_arch_register_cpu(int num)

arch/x86/xen/enlighten_hvm.c

···
+#include <linux/cpu.h>
+#include <linux/kexec.h>
+
+#include <xen/features.h>
+#include <xen/events.h>
+#include <xen/interface/memory.h>
+
+#include <asm/cpu.h>
+#include <asm/smp.h>
+#include <asm/reboot.h>
+#include <asm/setup.h>
+#include <asm/hypervisor.h>
+
+#include <asm/xen/cpuid.h>
+#include <asm/xen/hypervisor.h>
+
+#include "xen-ops.h"
+#include "mmu.h"
+#include "smp.h"
+
+void __ref xen_hvm_init_shared_info(void)
+{
+	int cpu;
+	struct xen_add_to_physmap xatp;
+	static struct shared_info *shared_info_page;
+
+	if (!shared_info_page)
+		shared_info_page = (struct shared_info *)
+			extend_brk(PAGE_SIZE, PAGE_SIZE);
+	xatp.domid = DOMID_SELF;
+	xatp.idx = 0;
+	xatp.space = XENMAPSPACE_shared_info;
+	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
+	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
+		BUG();
+
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
+
+	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
+	 * page, we use it in the event channel upcall and in some pvclock
+	 * related functions. We don't need the vcpu_info placement
+	 * optimizations because we don't use any pv_mmu or pv_irq op on
+	 * HVM.
+	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+	 * online but xen_hvm_init_shared_info is run at resume time too and
+	 * in that case multiple vcpus might be online. */
+	for_each_online_cpu(cpu) {
+		/* Leave it to be NULL. */
+		if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
+			continue;
+		per_cpu(xen_vcpu, cpu) =
+			&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
+	}
+}
+
+static void __init init_hvm_pv_info(void)
+{
+	int major, minor;
+	uint32_t eax, ebx, ecx, edx, base;
+
+	base = xen_cpuid_base();
+	eax = cpuid_eax(base + 1);
+
+	major = eax >> 16;
+	minor = eax & 0xffff;
+	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
+
+	xen_domain_type = XEN_HVM_DOMAIN;
+
+	/* PVH set up hypercall page in xen_prepare_pvh(). */
+	if (xen_pvh_domain())
+		pv_info.name = "Xen PVH";
+	else {
+		u64 pfn;
+		uint32_t msr;
+
+		pv_info.name = "Xen HVM";
+		msr = cpuid_ebx(base + 2);
+		pfn = __pa(hypercall_page);
+		wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+	}
+
+	xen_setup_features();
+
+	cpuid(base + 4, &eax, &ebx, &ecx, &edx);
+	if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
+		this_cpu_write(xen_vcpu_id, ebx);
+	else
+		this_cpu_write(xen_vcpu_id, smp_processor_id());
+}
+
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
+static int xen_cpu_up_prepare_hvm(unsigned int cpu)
+{
+	int rc;
+
+	/*
+	 * This can happen if CPU was offlined earlier and
+	 * offlining timed out in common_cpu_die().
+	 */
+	if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+	}
+
+	if (cpu_acpi_id(cpu) != U32_MAX)
+		per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
+	else
+		per_cpu(xen_vcpu_id, cpu) = cpu;
+	xen_vcpu_setup(cpu);
+
+	if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+		xen_setup_timer(cpu);
+
+	rc = xen_smp_intr_init(cpu);
+	if (rc) {
+		WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n",
+		     cpu, rc);
+		return rc;
+	}
+	return 0;
+}
+
+static int xen_cpu_dead_hvm(unsigned int cpu)
+{
+	xen_smp_intr_free(cpu);
+
+	if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+		xen_teardown_timer(cpu);
+
+       return 0;
+}
+
+static void __init xen_hvm_guest_init(void)
+{
+	if (xen_pv_domain())
+		return;
+
+	init_hvm_pv_info();
+
+	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();
+	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_hvm, xen_cpu_dead_hvm));
+	xen_unplug_emulated_devices();
+	x86_init.irqs.intr_init = xen_init_IRQ;
+	xen_hvm_init_time_ops();
+	xen_hvm_init_mmu_ops();
+
+	if (xen_pvh_domain())
+		machine_ops.emergency_restart = xen_emergency_restart;
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
+}
+
+static bool xen_nopv;
+static __init int xen_parse_nopv(char *arg)
+{
+       xen_nopv = true;
+       return 0;
+}
+early_param("xen_nopv", xen_parse_nopv);
+
+bool xen_hvm_need_lapic(void)
+{
+	if (xen_nopv)
+		return false;
+	if (xen_pv_domain())
+		return false;
+	if (!xen_hvm_domain())
+		return false;
+	if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
+
+static uint32_t __init xen_platform_hvm(void)
+{
+	if (xen_pv_domain() || xen_nopv)
+		return 0;
+
+	return xen_cpuid_base();
+}
+
+const struct hypervisor_x86 x86_hyper_xen_hvm = {
+	.name                   = "Xen HVM",
+	.detect                 = xen_platform_hvm,
+	.init_platform          = xen_hvm_guest_init,
+	.pin_vcpu               = xen_pin_vcpu,
+	.x2apic_available       = xen_x2apic_para_available,
+};
+EXPORT_SYMBOL(x86_hyper_xen_hvm);

arch/x86/xen/enlighten_pv.c

···
+/*
+ * Core of Xen paravirt_ops implementation.
+ *
+ * This file contains the xen_paravirt_ops structure itself, and the
+ * implementations for:
+ * - privileged instructions
+ * - interrupt flags
+ * - segment operations
+ * - booting and setup
+ *
+ * Jeremy Fitzhardinge <[e-mail]>, XenSource Inc, 2007
+ */
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/preempt.h>
+#include <linux/hardirq.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/start_kernel.h>
+#include <linux/sched.h>
+#include <linux/kprobes.h>
+#include <linux/bootmem.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/page-flags.h>
+#include <linux/highmem.h>
+#include <linux/console.h>
+#include <linux/pci.h>
+#include <linux/gfp.h>
+#include <linux/memblock.h>
+#include <linux/edd.h>
+#include <linux/frame.h>
+
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+#include <xen/interface/physdev.h>
+#include <xen/interface/vcpu.h>
+#include <xen/interface/memory.h>
+#include <xen/interface/nmi.h>
+#include <xen/interface/xen-mca.h>
+#include <xen/features.h>
+#include <xen/page.h>
+#include <xen/hvc-console.h>
+#include <xen/acpi.h>
+
+#include <asm/paravirt.h>
+#include <asm/apic.h>
+#include <asm/page.h>
+#include <asm/xen/pci.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/cpuid.h>
+#include <asm/fixmap.h>
+#include <asm/processor.h>
+#include <asm/proto.h>
+#include <asm/msr-index.h>
+#include <asm/traps.h>
+#include <asm/setup.h>
+#include <asm/desc.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/reboot.h>
+#include <asm/stackprotector.h>
+#include <asm/hypervisor.h>
+#include <asm/mach_traps.h>
+#include <asm/mwait.h>
+#include <asm/pci_x86.h>
+#include <asm/cpu.h>
+
+#ifdef CONFIG_ACPI
+#include <linux/acpi.h>
+#include <asm/acpi.h>
+#include <acpi/pdc_intel.h>
+#include <acpi/processor.h>
+#include <xen/interface/platform.h>
+#endif
+
+#include "xen-ops.h"
+#include "mmu.h"
+#include "smp.h"
+#include "multicalls.h"
+#include "pmu.h"
+
+void *xen_initial_gdt;
+
+RESERVE_BRK(shared_info_page_brk, PAGE_SIZE);
+
+static int xen_cpu_up_prepare_pv(unsigned int cpu);
+static int xen_cpu_dead_pv(unsigned int cpu);
+
+struct tls_descs {
+	struct desc_struct desc[3];
+};
+
+/*
+ * Updating the 3 TLS descriptors in the GDT on every task switch is
+ * surprisingly expensive so we avoid updating them if they haven't
+ * changed.  Since Xen writes different descriptors than the one
+ * passed in the update_descriptor hypercall we keep shadow copies to
+ * compare against.
+ */
+static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
+
+/*
+ * On restore, set the vcpu placement up again.
+ * If it fails, then we're in a bad state, since
+ * we can't back out from using it...
+ */
+void xen_vcpu_restore(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		bool other_cpu = (cpu != smp_processor_id());
+		bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu),
+						NULL);
+
+		if (other_cpu && is_up &&
+		    HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
+			BUG();
+
+		xen_setup_runstate_info(cpu);
+
+		if (xen_have_vcpu_info_placement)
+			xen_vcpu_setup(cpu);
+
+		if (other_cpu && is_up &&
+		    HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
+			BUG();
+	}
+}
+
+static void __init xen_banner(void)
+{
+	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	struct xen_extraversion extra;
+	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
+
+	pr_info("Booting paravirtualized kernel %son %s\n",
+		xen_feature(XENFEAT_auto_translated_physmap) ?
+			"with PVH extensions " : "", pv_info.name);
+	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
+	       version >> 16, version & 0xffff, extra.extraversion,
+	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
+}
+/* Check if running on Xen version (major, minor) or later */
+bool
+xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+	unsigned int version;
+
+	if (!xen_domain())
+		return false;
+
+	version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+		((version >> 16) > major))
+		return true;
+	return false;
+}
+
+static __read_mostly unsigned int cpuid_leaf5_ecx_val;
+static __read_mostly unsigned int cpuid_leaf5_edx_val;
+
+static void xen_cpuid(unsigned int *ax, unsigned int *bx,
+		      unsigned int *cx, unsigned int *dx)
+{
+	unsigned maskebx = ~0;
+
+	/*
+	 * Mask out inconvenient features, to try and disable as many
+	 * unsupported kernel subsystems as possible.
+	 */
+	switch (*ax) {
+	case CPUID_MWAIT_LEAF:
+		/* Synthesize the values.. */
+		*ax = 0;
+		*bx = 0;
+		*cx = cpuid_leaf5_ecx_val;
+		*dx = cpuid_leaf5_edx_val;
+		return;
+
+	case 0xb:
+		/* Suppress extended topology stuff */
+		maskebx = 0;
+		break;
+	}
+
+	asm(XEN_EMULATE_PREFIX "cpuid"
+		: "=a" (*ax),
+		  "=b" (*bx),
+		  "=c" (*cx),
+		  "=d" (*dx)
+		: "0" (*ax), "2" (*cx));
+
+	*bx &= maskebx;
+}
+STACK_FRAME_NON_STANDARD(xen_cpuid); /* XEN_EMULATE_PREFIX */
+
+static bool __init xen_check_mwait(void)
+{
+#ifdef CONFIG_ACPI
+	struct xen_platform_op op = {
+		.cmd			= XENPF_set_processor_pminfo,
+		.u.set_pminfo.id	= -1,
+		.u.set_pminfo.type	= XEN_PM_PDC,
+	};
+	uint32_t buf[3];
+	unsigned int ax, bx, cx, dx;
+	unsigned int mwait_mask;
+
+	/* We need to determine whether it is OK to expose the MWAIT
+	 * capability to the kernel to harvest deeper than C3 states from ACPI
+	 * _CST using the processor_harvest_xen.c module. For this to work, we
+	 * need to gather the MWAIT_LEAF values (which the cstate.c code
+	 * checks against). The hypervisor won't expose the MWAIT flag because
+	 * it would break backwards compatibility; so we will find out directly
+	 * from the hardware and hypercall.
+	 */
+	if (!xen_initial_domain())
+		return false;
+
+	/*
+	 * When running under platform earlier than Xen4.2, do not expose
+	 * mwait, to avoid the risk of loading native acpi pad driver
+	 */
+	if (!xen_running_on_version_or_later(4, 2))
+		return false;
+
+	ax = 1;
+	cx = 0;
+
+	native_cpuid(&ax, &bx, &cx, &dx);
+
+	mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
+		     (1 << (X86_FEATURE_MWAIT % 32));
+
+	if ((cx & mwait_mask) != mwait_mask)
+		return false;
+
+	/* We need to emulate the MWAIT_LEAF and for that we need both
+	 * ecx and edx. The hypercall provides only partial information.
+	 */
+
+	ax = CPUID_MWAIT_LEAF;
+	bx = 0;
+	cx = 0;
+	dx = 0;
+
+	native_cpuid(&ax, &bx, &cx, &dx);
+
+	/* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
+	 * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
+	 */
+	buf[0] = ACPI_PDC_REVISION_ID;
+	buf[1] = 1;
+	buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
+
+	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+
+	if ((HYPERVISOR_platform_op(&op) == 0) &&
+	    (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
+		cpuid_leaf5_ecx_val = cx;
+		cpuid_leaf5_edx_val = dx;
+	}
+	return true;
+#else
+	return false;
+#endif
+}
+
+static bool __init xen_check_xsave(void)
+{
+	unsigned int err, eax, edx;
+
+	/*
+	 * Xen 4.0 and older accidentally leaked the host XSAVE flag into guest
+	 * view, despite not being able to support guests using the
+	 * functionality. Probe for the actual availability of XSAVE by seeing
+	 * whether xgetbv executes successfully or raises #UD.
+	 */
+	asm volatile("1: .byte 0x0f,0x01,0xd0\n\t" /* xgetbv */
+		     "xor %[err], %[err]\n"
+		     "2:\n\t"
+		     ".pushsection .fixup,\"ax\"\n\t"
+		     "3: movl $1,%[err]\n\t"
+		     "jmp 2b\n\t"
+		     ".popsection\n\t"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), "=a" (eax), "=d" (edx)
+		     : "c" (0));
+
+	return err == 0;
+}
+
+static void __init xen_init_capabilities(void)
+{
+	setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS);
+	setup_force_cpu_cap(X86_FEATURE_XENPV);
+	setup_clear_cpu_cap(X86_FEATURE_DCA);
+	setup_clear_cpu_cap(X86_FEATURE_APERFMPERF);
+	setup_clear_cpu_cap(X86_FEATURE_MTRR);
+	setup_clear_cpu_cap(X86_FEATURE_ACC);
+	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
+
+	if (!xen_initial_domain())
+		setup_clear_cpu_cap(X86_FEATURE_ACPI);
+
+	if (xen_check_mwait())
+		setup_force_cpu_cap(X86_FEATURE_MWAIT);
+	else
+		setup_clear_cpu_cap(X86_FEATURE_MWAIT);
+
+	if (xen_check_xsave()) {
+		setup_force_cpu_cap(X86_FEATURE_XSAVE);
+		setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+	} else {
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_OSXSAVE);
+	}
+}
+
+static void xen_set_debugreg(int reg, unsigned long val)
+{
+	HYPERVISOR_set_debugreg(reg, val);
+}
+
+static unsigned long xen_get_debugreg(int reg)
+{
+	return HYPERVISOR_get_debugreg(reg);
+}
+
+static void xen_end_context_switch(struct task_struct *next)
+{
+	xen_mc_flush();
+	paravirt_end_context_switch(next);
+}
+
+static unsigned long xen_store_tr(void)
+{
+	return 0;
+}
+
+/*
+ * Set the page permissions for a particular virtual address.  If the
+ * address is a vmalloc mapping (or other non-linear mapping), then
+ * find the linear mapping of the page and also set its protections to
+ * match.
+ */
+static void set_aliased_prot(void *v, pgprot_t prot)
+{
+	int level;
+	pte_t *ptep;
+	pte_t pte;
+	unsigned long pfn;
+	struct page *page;
+	unsigned char dummy;
+
+	ptep = lookup_address((unsigned long)v, &level);
+	BUG_ON(ptep == NULL);
+
+	pfn = pte_pfn(*ptep);
+	page = pfn_to_page(pfn);
+
+	pte = pfn_pte(pfn, prot);
+
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	probe_kernel_read(&dummy, v, 1);
+
+	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
+		BUG();
+
+	if (!PageHighMem(page)) {
+		void *av = __va(PFN_PHYS(pfn));
+
+		if (av != v)
+			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
+				BUG();
+	} else
+		kmap_flush_unused();
+
+	preempt_enable();
+}
+
+static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
+	int i;
+
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
+	for (i = 0; i < entries; i += entries_per_page)
+		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
+}
+
+static void xen_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
+	int i;
+
+	for (i = 0; i < entries; i += entries_per_page)
+		set_aliased_prot(ldt + i, PAGE_KERNEL);
+}
+
+static void xen_set_ldt(const void *addr, unsigned entries)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs = xen_mc_entry(sizeof(*op));
+
+	trace_xen_cpu_set_ldt(addr, entries);
+
+	op = mcs.args;
+	op->cmd = MMUEXT_SET_LDT;
+	op->arg1.linear_addr = (unsigned long)addr;
+	op->arg2.nr_ents = entries;
+
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_load_gdt(const struct desc_ptr *dtr)
+{
+	unsigned long va = dtr->address;
+	unsigned int size = dtr->size + 1;
+	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
+	unsigned long frames[pages];
+	int f;
+
+	/*
+	 * A GDT can be up to 64k in size, which corresponds to 8192
+	 * 8-byte entries, or 16 4k pages..
+	 */
+
+	BUG_ON(size > 65536);
+	BUG_ON(va & ~PAGE_MASK);
+
+	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
+		int level;
+		pte_t *ptep;
+		unsigned long pfn, mfn;
+		void *virt;
+
+		/*
+		 * The GDT is per-cpu and is in the percpu data area.
+		 * That can be virtually mapped, so we need to do a
+		 * page-walk to get the underlying MFN for the
+		 * hypercall.  The page can also be in the kernel's
+		 * linear range, so we need to RO that mapping too.
+		 */
+		ptep = lookup_address(va, &level);
+		BUG_ON(ptep == NULL);
+
+		pfn = pte_pfn(*ptep);
+		mfn = pfn_to_mfn(pfn);
+		virt = __va(PFN_PHYS(pfn));
+
+		frames[f] = mfn;
+
+		make_lowmem_page_readonly((void *)va);
+		make_lowmem_page_readonly(virt);
+	}
+
+	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+		BUG();
+}
+
+/*
+ * load_gdt for early boot, when the gdt is only mapped once
+ */
+static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
+{
+	unsigned long va = dtr->address;
+	unsigned int size = dtr->size + 1;
+	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
+	unsigned long frames[pages];
+	int f;
+
+	/*
+	 * A GDT can be up to 64k in size, which corresponds to 8192
+	 * 8-byte entries, or 16 4k pages..
+	 */
+
+	BUG_ON(size > 65536);
+	BUG_ON(va & ~PAGE_MASK);
+
+	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
+		pte_t pte;
+		unsigned long pfn, mfn;
+
+		pfn = virt_to_pfn(va);
+		mfn = pfn_to_mfn(pfn);
+
+		pte = pfn_pte(pfn, PAGE_KERNEL_RO);
+
+		if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+			BUG();
+
+		frames[f] = mfn;
+	}
+
+	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+		BUG();
+}
+
+static inline bool desc_equal(const struct desc_struct *d1,
+			      const struct desc_struct *d2)
+{
+	return d1->a == d2->a && d1->b == d2->b;
+}
+
+static void load_TLS_descriptor(struct thread_struct *t,
+				unsigned int cpu, unsigned int i)
+{
+	struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i];
+	struct desc_struct *gdt;
+	xmaddr_t maddr;
+	struct multicall_space mc;
+
+	if (desc_equal(shadow, &t->tls_array[i]))
+		return;
+
+	*shadow = t->tls_array[i];
+
+	gdt = get_cpu_gdt_rw(cpu);
+	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
+	mc = __xen_mc_entry(0);
+
+	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
+}
+
+static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	/*
+	 * XXX sleazy hack: If we're being called in a lazy-cpu zone
+	 * and lazy gs handling is enabled, it means we're in a
+	 * context switch, and %gs has just been saved.  This means we
+	 * can zero it out to prevent faults on exit from the
+	 * hypervisor if the next process has no %gs.  Either way, it
+	 * has been saved, and the new value will get loaded properly.
+	 * This will go away as soon as Xen has been modified to not
+	 * save/restore %gs for normal hypercalls.
+	 *
+	 * On x86_64, this hack is not used for %gs, because gs points
+	 * to KERNEL_GS_BASE (and uses it for PDA references), so we
+	 * must not zero %gs on x86_64
+	 *
+	 * For x86_64, we need to zero %fs, otherwise we may get an
+	 * exception between the new %fs descriptor being loaded and
+	 * %fs being effectively cleared at __switch_to().
+	 */
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+#ifdef CONFIG_X86_32
+		lazy_load_gs(0);
+#else
+		loadsegment(fs, 0);
+#endif
+	}
+
+	xen_mc_batch();
+
+	load_TLS_descriptor(t, cpu, 0);
+	load_TLS_descriptor(t, cpu, 1);
+	load_TLS_descriptor(t, cpu, 2);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+#ifdef CONFIG_X86_64
+static void xen_load_gs_index(unsigned int idx)
+{
+	if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
+		BUG();
+}
+#endif
+
+static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
+				const void *ptr)
+{
+	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
+	u64 entry = *(u64 *)ptr;
+
+	trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
+
+	preempt_disable();
+
+	xen_mc_flush();
+	if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry))
+		BUG();
+
+	preempt_enable();
+}
+
+static int cvt_gate_to_trap(int vector, const gate_desc *val,
+			    struct trap_info *info)
+{
+	unsigned long addr;
+
+	if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
+		return 0;
+
+	info->vector = vector;
+
+	addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+	/*
+	 * Look for known traps using IST, and substitute them
+	 * appropriately.  The debugger ones are the only ones we care
+	 * about.  Xen will handle faults like double_fault,
+	 * so we should never see them.  Warn if
+	 * there's an unexpected IST-using fault handler.
+	 */
+	if (addr == (unsigned long)debug)
+		addr = (unsigned long)xen_debug;
+	else if (addr == (unsigned long)int3)
+		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) {
+		/* Don't need to handle these */
+		return 0;
+#ifdef CONFIG_X86_MCE
+	} else if (addr == (unsigned long)machine_check) {
+		/*
+		 * when xen hypervisor inject vMCE to guest,
+		 * use native mce handler to handle it
+		 */
+		;
+#endif
+	} 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;
+	}
+#endif	/* CONFIG_X86_64 */
+	info->address = addr;
+
+	info->cs = gate_segment(*val);
+	info->flags = val->dpl;
+	/* interrupt gates clear IF */
+	if (val->type == GATE_INTERRUPT)
+		info->flags |= 1 << 2;
+
+	return 1;
+}
+
+/* Locations of each CPU's IDT */
+static DEFINE_PER_CPU(struct desc_ptr, idt_desc);
+
+/* Set an IDT entry.  If the entry is part of the current IDT, then
+   also update Xen. */
+static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
+{
+	unsigned long p = (unsigned long)&dt[entrynum];
+	unsigned long start, end;
+
+	trace_xen_cpu_write_idt_entry(dt, entrynum, g);
+
+	preempt_disable();
+
+	start = __this_cpu_read(idt_desc.address);
+	end = start + __this_cpu_read(idt_desc.size) + 1;
+
+	xen_mc_flush();
+
+	native_write_idt_entry(dt, entrynum, g);
+
+	if (p >= start && (p + 8) <= end) {
+		struct trap_info info[2];
+
+		info[1].address = 0;
+
+		if (cvt_gate_to_trap(entrynum, g, &info[0]))
+			if (HYPERVISOR_set_trap_table(info))
+				BUG();
+	}
+
+	preempt_enable();
+}
+
+static void xen_convert_trap_info(const struct desc_ptr *desc,
+				  struct trap_info *traps)
+{
+	unsigned in, out, count;
+
+	count = (desc->size+1) / sizeof(gate_desc);
+	BUG_ON(count > 256);
+
+	for (in = out = 0; in < count; in++) {
+		gate_desc *entry = (gate_desc *)(desc->address) + in;
+
+		if (cvt_gate_to_trap(in, entry, &traps[out]))
+			out++;
+	}
+	traps[out].address = 0;
+}
+
+void xen_copy_trap_info(struct trap_info *traps)
+{
+	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
+
+	xen_convert_trap_info(desc, traps);
+}
+
+/* Load a new IDT into Xen.  In principle this can be per-CPU, so we
+   hold a spinlock to protect the static traps[] array (static because
+   it avoids allocation, and saves stack space). */
+static void xen_load_idt(const struct desc_ptr *desc)
+{
+	static DEFINE_SPINLOCK(lock);
+	static struct trap_info traps[257];
+
+	trace_xen_cpu_load_idt(desc);
+
+	spin_lock(&lock);
+
+	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
+
+	xen_convert_trap_info(desc, traps);
+
+	xen_mc_flush();
+	if (HYPERVISOR_set_trap_table(traps))
+		BUG();
+
+	spin_unlock(&lock);
+}
+
+/* Write a GDT descriptor entry.  Ignore LDT descriptors, since
+   they're handled differently. */
+static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
+				const void *desc, int type)
+{
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
+	preempt_disable();
+
+	switch (type) {
+	case DESC_LDT:
+	case DESC_TSS:
+		/* ignore */
+		break;
+
+	default: {
+		xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]);
+
+		xen_mc_flush();
+		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
+			BUG();
+	}
+
+	}
+
+	preempt_enable();
+}
+
+/*
+ * Version of write_gdt_entry for use at early boot-time needed to
+ * update an entry as simply as possible.
+ */
+static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
+					    const void *desc, int type)
+{
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
+	switch (type) {
+	case DESC_LDT:
+	case DESC_TSS:
+		/* ignore */
+		break;
+
+	default: {
+		xmaddr_t maddr = virt_to_machine(&dt[entry]);
+
+		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
+			dt[entry] = *(struct desc_struct *)desc;
+	}
+
+	}
+}
+
+static void xen_load_sp0(struct tss_struct *tss,
+			 struct thread_struct *thread)
+{
+	struct multicall_space mcs;
+
+	mcs = xen_mc_entry(0);
+	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	tss->x86_tss.sp0 = thread->sp0;
+}
+
+void xen_set_iopl_mask(unsigned mask)
+{
+	struct physdev_set_iopl set_iopl;
+
+	/* Force the change at ring 0. */
+	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
+	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+}
+
+static void xen_io_delay(void)
+{
+}
+
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+	unsigned long cr0 = this_cpu_read(xen_cr0_value);
+
+	if (unlikely(cr0 == 0)) {
+		cr0 = native_read_cr0();
+		this_cpu_write(xen_cr0_value, cr0);
+	}
+
+	return cr0;
+}
+
+static void xen_write_cr0(unsigned long cr0)
+{
+	struct multicall_space mcs;
+
+	this_cpu_write(xen_cr0_value, cr0);
+
+	/* Only pay attention to cr0.TS; everything else is
+	   ignored. */
+	mcs = xen_mc_entry(0);
+
+	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_write_cr4(unsigned long cr4)
+{
+	cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE);
+
+	native_write_cr4(cr4);
+}
+#ifdef CONFIG_X86_64
+static inline unsigned long xen_read_cr8(void)
+{
+	return 0;
+}
+static inline void xen_write_cr8(unsigned long val)
+{
+	BUG_ON(val);
+}
+#endif
+
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+	u64 val;
+
+	if (pmu_msr_read(msr, &val, err))
+		return val;
+
+	val = native_read_msr_safe(msr, err);
+	switch (msr) {
+	case MSR_IA32_APICBASE:
+#ifdef CONFIG_X86_X2APIC
+		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
+#endif
+			val &= ~X2APIC_ENABLE;
+		break;
+	}
+	return val;
+}
+
+static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
+{
+	int ret;
+
+	ret = 0;
+
+	switch (msr) {
+#ifdef CONFIG_X86_64
+		unsigned which;
+		u64 base;
+
+	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
+	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
+	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
+
+	set:
+		base = ((u64)high << 32) | low;
+		if (HYPERVISOR_set_segment_base(which, base) != 0)
+			ret = -EIO;
+		break;
+#endif
+
+	case MSR_STAR:
+	case MSR_CSTAR:
+	case MSR_LSTAR:
+	case MSR_SYSCALL_MASK:
+	case MSR_IA32_SYSENTER_CS:
+	case MSR_IA32_SYSENTER_ESP:
+	case MSR_IA32_SYSENTER_EIP:
+		/* Fast syscall setup is all done in hypercalls, so
+		   these are all ignored.  Stub them out here to stop
+		   Xen console noise. */
+		break;
+
+	default:
+		if (!pmu_msr_write(msr, low, high, &ret))
+			ret = native_write_msr_safe(msr, low, high);
+	}
+
+	return ret;
+}
+
+static u64 xen_read_msr(unsigned int msr)
+{
+	/*
+	 * This will silently swallow a #GP from RDMSR.  It may be worth
+	 * changing that.
+	 */
+	int err;
+
+	return xen_read_msr_safe(msr, &err);
+}
+
+static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+{
+	/*
+	 * This will silently swallow a #GP from WRMSR.  It may be worth
+	 * changing that.
+	 */
+	xen_write_msr_safe(msr, low, high);
+}
+
+void xen_setup_shared_info(void)
+{
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		set_fixmap(FIX_PARAVIRT_BOOTMAP,
+			   xen_start_info->shared_info);
+
+		HYPERVISOR_shared_info =
+			(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+	} else
+		HYPERVISOR_shared_info =
+			(struct shared_info *)__va(xen_start_info->shared_info);
+
+#ifndef CONFIG_SMP
+	/* In UP this is as good a place as any to set up shared info */
+	xen_setup_vcpu_info_placement();
+#endif
+
+	xen_setup_mfn_list_list();
+}
+
+/* This is called once we have the cpu_possible_mask */
+void xen_setup_vcpu_info_placement(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		/* Set up direct vCPU id mapping for PV guests. */
+		per_cpu(xen_vcpu_id, cpu) = cpu;
+		xen_vcpu_setup(cpu);
+	}
+
+	/*
+	 * xen_vcpu_setup managed to place the vcpu_info within the
+	 * percpu area for all cpus, so make use of it.
+	 */
+	if (xen_have_vcpu_info_placement) {
+		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
+		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
+		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
+		pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
+		pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
+	}
+}
+
+static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
+			  unsigned long addr, unsigned len)
+{
+	char *start, *end, *reloc;
+	unsigned ret;
+
+	start = end = reloc = NULL;
+
+#define SITE(op, x)							\
+	case PARAVIRT_PATCH(op.x):					\
+	if (xen_have_vcpu_info_placement) {				\
+		start = (char *)xen_##x##_direct;			\
+		end = xen_##x##_direct_end;				\
+		reloc = xen_##x##_direct_reloc;				\
+	}								\
+	goto patch_site
+
+	switch (type) {
+		SITE(pv_irq_ops, irq_enable);
+		SITE(pv_irq_ops, irq_disable);
+		SITE(pv_irq_ops, save_fl);
+		SITE(pv_irq_ops, restore_fl);
+#undef SITE
+
+	patch_site:
+		if (start == NULL || (end-start) > len)
+			goto default_patch;
+
+		ret = paravirt_patch_insns(insnbuf, len, start, end);
+
+		/* Note: because reloc is assigned from something that
+		   appears to be an array, gcc assumes it's non-null,
+		   but doesn't know its relationship with start and
+		   end. */
+		if (reloc > start && reloc < end) {
+			int reloc_off = reloc - start;
+			long *relocp = (long *)(insnbuf + reloc_off);
+			long delta = start - (char *)addr;
+
+			*relocp += delta;
+		}
+		break;
+
+	default_patch:
+	default:
+		ret = paravirt_patch_default(type, clobbers, insnbuf,
+					     addr, len);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct pv_info xen_info __initconst = {
+	.shared_kernel_pmd = 0,
+
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+	.name = "Xen",
+};
+
+static const struct pv_init_ops xen_init_ops __initconst = {
+	.patch = xen_patch,
+};
+
+static const struct pv_cpu_ops xen_cpu_ops __initconst = {
+	.cpuid = xen_cpuid,
+
+	.set_debugreg = xen_set_debugreg,
+	.get_debugreg = xen_get_debugreg,
+
+	.read_cr0 = xen_read_cr0,
+	.write_cr0 = xen_write_cr0,
+
+	.read_cr4 = native_read_cr4,
+	.write_cr4 = xen_write_cr4,
+
+#ifdef CONFIG_X86_64
+	.read_cr8 = xen_read_cr8,
+	.write_cr8 = xen_write_cr8,
+#endif
+
+	.wbinvd = native_wbinvd,
+
+	.read_msr = xen_read_msr,
+	.write_msr = xen_write_msr,
+
+	.read_msr_safe = xen_read_msr_safe,
+	.write_msr_safe = xen_write_msr_safe,
+
+	.read_pmc = xen_read_pmc,
+
+	.iret = xen_iret,
+#ifdef CONFIG_X86_64
+	.usergs_sysret64 = xen_sysret64,
+#endif
+
+	.load_tr_desc = paravirt_nop,
+	.set_ldt = xen_set_ldt,
+	.load_gdt = xen_load_gdt,
+	.load_idt = xen_load_idt,
+	.load_tls = xen_load_tls,
+#ifdef CONFIG_X86_64
+	.load_gs_index = xen_load_gs_index,
+#endif
+
+	.alloc_ldt = xen_alloc_ldt,
+	.free_ldt = xen_free_ldt,
+
+	.store_idt = native_store_idt,
+	.store_tr = xen_store_tr,
+
+	.write_ldt_entry = xen_write_ldt_entry,
+	.write_gdt_entry = xen_write_gdt_entry,
+	.write_idt_entry = xen_write_idt_entry,
+	.load_sp0 = xen_load_sp0,
+
+	.set_iopl_mask = xen_set_iopl_mask,
+	.io_delay = xen_io_delay,
+
+	/* Xen takes care of %gs when switching to usermode for us */
+	.swapgs = paravirt_nop,
+
+	.start_context_switch = paravirt_start_context_switch,
+	.end_context_switch = xen_end_context_switch,
+};
+
+static void xen_restart(char *msg)
+{
+	xen_reboot(SHUTDOWN_reboot);
+}
+
+static void xen_machine_halt(void)
+{
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
+static void xen_machine_power_off(void)
+{
+	if (pm_power_off)
+		pm_power_off();
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
+static void xen_crash_shutdown(struct pt_regs *regs)
+{
+	xen_reboot(SHUTDOWN_crash);
+}
+
+static const struct machine_ops xen_machine_ops __initconst = {
+	.restart = xen_restart,
+	.halt = xen_machine_halt,
+	.power_off = xen_machine_power_off,
+	.shutdown = xen_machine_halt,
+	.crash_shutdown = xen_crash_shutdown,
+	.emergency_restart = xen_emergency_restart,
+};
+
+static unsigned char xen_get_nmi_reason(void)
+{
+	unsigned char reason = 0;
+
+	/* Construct a value which looks like it came from port 0x61. */
+	if (test_bit(_XEN_NMIREASON_io_error,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_IOCHK;
+	if (test_bit(_XEN_NMIREASON_pci_serr,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_SERR;
+
+	return reason;
+}
+
+static void __init xen_boot_params_init_edd(void)
+{
+#if IS_ENABLED(CONFIG_EDD)
+	struct xen_platform_op op;
+	struct edd_info *edd_info;
+	u32 *mbr_signature;
+	unsigned nr;
+	int ret;
+
+	edd_info = boot_params.eddbuf;
+	mbr_signature = boot_params.edd_mbr_sig_buffer;
+
+	op.cmd = XENPF_firmware_info;
+
+	op.u.firmware_info.type = XEN_FW_DISK_INFO;
+	for (nr = 0; nr < EDDMAXNR; nr++) {
+		struct edd_info *info = edd_info + nr;
+
+		op.u.firmware_info.index = nr;
+		info->params.length = sizeof(info->params);
+		set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
+				     &info->params);
+		ret = HYPERVISOR_platform_op(&op);
+		if (ret)
+			break;
+
+#define C(x) info->x = op.u.firmware_info.u.disk_info.x
+		C(device);
+		C(version);
+		C(interface_support);
+		C(legacy_max_cylinder);
+		C(legacy_max_head);
+		C(legacy_sectors_per_track);
+#undef C
+	}
+	boot_params.eddbuf_entries = nr;
+
+	op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
+	for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
+		op.u.firmware_info.index = nr;
+		ret = HYPERVISOR_platform_op(&op);
+		if (ret)
+			break;
+		mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
+	}
+	boot_params.edd_mbr_sig_buf_entries = nr;
+#endif
+}
+
+/*
+ * Set up the GDT and segment registers for -fstack-protector.  Until
+ * we do this, we have to be careful not to call any stack-protected
+ * function, which is most of the kernel.
+ */
+static void xen_setup_gdt(int cpu)
+{
+	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
+	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
+
+	setup_stack_canary_segment(0);
+	switch_to_new_gdt(0);
+
+	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry;
+	pv_cpu_ops.load_gdt = xen_load_gdt;
+}
+
+static void __init xen_dom0_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 1;
+}
+
+/* First C function to be called on Xen boot */
+asmlinkage __visible void __init xen_start_kernel(void)
+{
+	struct physdev_set_iopl set_iopl;
+	unsigned long initrd_start = 0;
+	int rc;
+
+	if (!xen_start_info)
+		return;
+
+	xen_domain_type = XEN_PV_DOMAIN;
+
+	xen_setup_features();
+
+	xen_setup_machphys_mapping();
+
+	/* Install Xen paravirt ops */
+	pv_info = xen_info;
+	pv_init_ops = xen_init_ops;
+	pv_cpu_ops = xen_cpu_ops;
+
+	x86_platform.get_nmi_reason = xen_get_nmi_reason;
+
+	x86_init.resources.memory_setup = xen_memory_setup;
+	x86_init.oem.arch_setup = xen_arch_setup;
+	x86_init.oem.banner = xen_banner;
+
+	xen_init_time_ops();
+
+	/*
+	 * Set up some pagetable state before starting to set any ptes.
+	 */
+
+	xen_init_mmu_ops();
+
+	/* Prevent unwanted bits from being set in PTEs. */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+
+	/*
+	 * Prevent page tables from being allocated in highmem, even
+	 * if CONFIG_HIGHPTE is enabled.
+	 */
+	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+
+	/* Work out if we support NX */
+	x86_configure_nx();
+
+	/* Get mfn list */
+	xen_build_dynamic_phys_to_machine();
+
+	/*
+	 * Set up kernel GDT and segment registers, mainly so that
+	 * -fstack-protector code can be executed.
+	 */
+	xen_setup_gdt(0);
+
+	xen_init_irq_ops();
+	xen_init_capabilities();
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * set up the basic apic ops.
+	 */
+	xen_init_apic();
+#endif
+
+	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
+		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
+		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+	}
+
+	machine_ops = xen_machine_ops;
+
+	/*
+	 * The only reliable way to retain the initial address of the
+	 * percpu gdt_page is to remember it here, so we can go and
+	 * mark it RW later, when the initial percpu area is freed.
+	 */
+	xen_initial_gdt = &per_cpu(gdt_page, 0);
+
+	xen_smp_init();
+
+#ifdef CONFIG_ACPI_NUMA
+	/*
+	 * The pages we from Xen are not related to machine pages, so
+	 * any NUMA information the kernel tries to get from ACPI will
+	 * be meaningless.  Prevent it from trying.
+	 */
+	acpi_numa = -1;
+#endif
+	/* Don't do the full vcpu_info placement stuff until we have a
+	   possible map and a non-dummy shared_info. */
+	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
+
+	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
+
+	local_irq_disable();
+	early_boot_irqs_disabled = true;
+
+	xen_raw_console_write("mapping kernel into physical memory\n");
+	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
+				   xen_start_info->nr_pages);
+	xen_reserve_special_pages();
+
+	/* keep using Xen gdt for now; no urgent need to change it */
+
+#ifdef CONFIG_X86_32
+	pv_info.kernel_rpl = 1;
+	if (xen_feature(XENFEAT_supervisor_mode_kernel))
+		pv_info.kernel_rpl = 0;
+#else
+	pv_info.kernel_rpl = 0;
+#endif
+	/* set the limit of our address space */
+	xen_reserve_top();
+
+	/*
+	 * We used to do this in xen_arch_setup, but that is too late
+	 * on AMD were early_cpu_init (run before ->arch_setup()) calls
+	 * early_amd_init which pokes 0xcf8 port.
+	 */
+	set_iopl.iopl = 1;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+	if (rc != 0)
+		xen_raw_printk("physdev_op failed %d\n", rc);
+
+#ifdef CONFIG_X86_32
+	/* set up basic CPUID stuff */
+	cpu_detect(&new_cpu_data);
+	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
+	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
+#endif
+
+	if (xen_start_info->mod_start) {
+	    if (xen_start_info->flags & SIF_MOD_START_PFN)
+		initrd_start = PFN_PHYS(xen_start_info->mod_start);
+	    else
+		initrd_start = __pa(xen_start_info->mod_start);
+	}
+
+	/* Poke various useful things into boot_params */
+	boot_params.hdr.type_of_loader = (9 << 4) | 0;
+	boot_params.hdr.ramdisk_image = initrd_start;
+	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
+	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
+
+	if (!xen_initial_domain()) {
+		add_preferred_console("xenboot", 0, NULL);
+		add_preferred_console("tty", 0, NULL);
+		add_preferred_console("hvc", 0, NULL);
+		if (pci_xen)
+			x86_init.pci.arch_init = pci_xen_init;
+	} else {
+		const struct dom0_vga_console_info *info =
+			(void *)((char *)xen_start_info +
+				 xen_start_info->console.dom0.info_off);
+		struct xen_platform_op op = {
+			.cmd = XENPF_firmware_info,
+			.interface_version = XENPF_INTERFACE_VERSION,
+			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
+		};
+
+		x86_platform.set_legacy_features =
+				xen_dom0_set_legacy_features;
+		xen_init_vga(info, xen_start_info->console.dom0.info_size);
+		xen_start_info->console.domU.mfn = 0;
+		xen_start_info->console.domU.evtchn = 0;
+
+		if (HYPERVISOR_platform_op(&op) == 0)
+			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
+
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
+
+		xen_acpi_sleep_register();
+
+		/* Avoid searching for BIOS MP tables */
+		x86_init.mpparse.find_smp_config = x86_init_noop;
+		x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+
+		xen_boot_params_init_edd();
+	}
+#ifdef CONFIG_PCI
+	/* PCI BIOS service won't work from a PV guest. */
+	pci_probe &= ~PCI_PROBE_BIOS;
+#endif
+	xen_raw_console_write("about to get started...\n");
+
+	/* Let's presume PV guests always boot on vCPU with id 0. */
+	per_cpu(xen_vcpu_id, 0) = 0;
+
+	xen_setup_runstate_info(0);
+
+	xen_efi_init();
+
+	/* Start the world */
+#ifdef CONFIG_X86_32
+	i386_start_kernel();
+#else
+	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
+	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
+#endif
+}
+
+static int xen_cpu_up_prepare_pv(unsigned int cpu)
+{
+	int rc;
+
+	xen_setup_timer(cpu);
+
+	rc = xen_smp_intr_init(cpu);
+	if (rc) {
+		WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n",
+		     cpu, rc);
+		return rc;
+	}
+
+	rc = xen_smp_intr_init_pv(cpu);
+	if (rc) {
+		WARN(1, "xen_smp_intr_init_pv() for CPU %d failed: %d\n",
+		     cpu, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static int xen_cpu_dead_pv(unsigned int cpu)
+{
+	xen_smp_intr_free(cpu);
+	xen_smp_intr_free_pv(cpu);
+
+	xen_teardown_timer(cpu);
+
+	return 0;
+}
+
+static uint32_t __init xen_platform_pv(void)
+{
+	if (xen_pv_domain())
+		return xen_cpuid_base();
+
+	return 0;
+}
+
+const struct hypervisor_x86 x86_hyper_xen_pv = {
+	.name                   = "Xen PV",
+	.detect                 = xen_platform_pv,
+	.pin_vcpu               = xen_pin_vcpu,
+};
+EXPORT_SYMBOL(x86_hyper_xen_pv);

arch/x86/xen/enlighten_pvh.c

···
+#include <linux/acpi.h>
+
+#include <xen/hvc-console.h>
+
+#include <asm/io_apic.h>
+#include <asm/hypervisor.h>
+#include <asm/e820/api.h>
+
+#include <asm/xen/interface.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/memory.h>
+#include <xen/interface/hvm/start_info.h>
+
+/*
+ * PVH variables.
+ *
+ * xen_pvh and pvh_bootparams need to live in data segment since they
+ * are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+bool xen_pvh __attribute__((section(".data"))) = 0;
+struct boot_params pvh_bootparams __attribute__((section(".data")));
+
+struct hvm_start_info pvh_start_info;
+unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+
+static void xen_pvh_arch_setup(void)
+{
+	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
+	if (nr_ioapics == 0)
+		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
+}
+
+static void __init init_pvh_bootparams(void)
+{
+	struct xen_memory_map memmap;
+	int rc;
+
+	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table);
+	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table);
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc) {
+		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
+		BUG();
+	}
+	pvh_bootparams.e820_entries = memmap.nr_entries;
+
+	if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) {
+		pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr =
+			ISA_START_ADDRESS;
+		pvh_bootparams.e820_table[pvh_bootparams.e820_entries].size =
+			ISA_END_ADDRESS - ISA_START_ADDRESS;
+		pvh_bootparams.e820_table[pvh_bootparams.e820_entries].type =
+			E820_TYPE_RESERVED;
+		pvh_bootparams.e820_entries++;
+	} else
+		xen_raw_printk("Warning: Can fit ISA range into e820\n");
+
+	pvh_bootparams.hdr.cmd_line_ptr =
+		pvh_start_info.cmdline_paddr;
+
+	/* The first module is always ramdisk. */
+	if (pvh_start_info.nr_modules) {
+		struct hvm_modlist_entry *modaddr =
+			__va(pvh_start_info.modlist_paddr);
+		pvh_bootparams.hdr.ramdisk_image = modaddr->paddr;
+		pvh_bootparams.hdr.ramdisk_size = modaddr->size;
+	}
+
+	/*
+	 * See Documentation/x86/boot.txt.
+	 *
+	 * Version 2.12 supports Xen entry point but we will use default x86/PC
+	 * environment (i.e. hardware_subarch 0).
+	 */
+	pvh_bootparams.hdr.version = 0x212;
+	pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+}
+
+/*
+ * This routine (and those that it might call) should not use
+ * anything that lives in .bss since that segment will be cleared later.
+ */
+void __init xen_prepare_pvh(void)
+{
+	u32 msr;
+	u64 pfn;
+
+	if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
+		xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
+				pvh_start_info.magic);
+		BUG();
+	}
+
+	xen_pvh = 1;
+
+	msr = cpuid_ebx(xen_cpuid_base() + 2);
+	pfn = __pa(hypercall_page);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	init_pvh_bootparams();
+
+	x86_init.oem.arch_setup = xen_pvh_arch_setup;
+}

arch/x86/xen/mmu.c

···
-/*
- * Xen mmu operations
- *
- * This file contains the various mmu fetch and update operations.
- * The most important job they must perform is the mapping between the
- * domain's pfn and the overall machine mfns.
- *
- * Xen allows guests to directly update the pagetable, in a controlled
- * fashion.  In other words, the guest modifies the same pagetable
- * that the CPU actually uses, which eliminates the overhead of having
- * a separate shadow pagetable.
- *
- * In order to allow this, it falls on the guest domain to map its
- * notion of a "physical" pfn - which is just a domain-local linear
- * address - into a real "machine address" which the CPU's MMU can
- * use.
- *
- * A pgd_t/pmd_t/pte_t will typically contain an mfn, and so can be
- * inserted directly into the pagetable.  When creating a new
- * pte/pmd/pgd, it converts the passed pfn into an mfn.  Conversely,
- * when reading the content back with __(pgd|pmd|pte)_val, it converts
- * the mfn back into a pfn.
- *
- * The other constraint is that all pages which 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 a
- * pagetable page RW, and will disallow using any writable page as a
- * pagetable.
- *
- * Naively, when loading %cr3 with the base of a new pagetable, Xen
- * would need to validate the whole pagetable before going on.
- * Naturally, this is quite slow.  The solution is to "pin" a
- * pagetable, which enforces all the constraints on the pagetable even
- * when it is not actively in use.  This menas that Xen can be assured
- * that it is still valid when you do load it into %cr3, and doesn't
- * need to revalidate it.
- *
- * Jeremy Fitzhardinge <[e-mail]>, XenSource Inc, 2007
- */
-#include <linux/sched/mm.h>
-#include <linux/highmem.h>
-#include <linux/debugfs.h>
-#include <linux/bug.h>
-#include <linux/vmalloc.h>
-#include <linux/export.h>
-#include <linux/init.h>
-#include <linux/gfp.h>
-#include <linux/memblock.h>
-#include <linux/seq_file.h>
-#include <linux/crash_dump.h>
-
-#include <trace/events/xen.h>
-
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <asm/fixmap.h>
-#include <asm/mmu_context.h>
-#include <asm/setup.h>
-#include <asm/paravirt.h>
-#include <asm/e820/api.h>
-#include <asm/linkage.h>
-#include <asm/page.h>
-#include <asm/init.h>
-#include <asm/pat.h>
-#include <asm/smp.h>
-
+#include <linux/pfn.h>
+#include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
-#include <asm/xen/hypervisor.h>
-
-#include <xen/xen.h>
-#include <xen/page.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/hvm/hvm_op.h>
-#include <xen/interface/version.h>
 #include <xen/interface/memory.h>
-#include <xen/hvc-console.h>
 
 #include "multicalls.h"
 #include "mmu.h"
-#include "debugfs.h"
 
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
  * Also protects non-atomic updates of current_pages and balloon lists.
  */
 DEFINE_SPINLOCK(xen_reservation_lock);
-
-#ifdef CONFIG_X86_32
-/*
- * Identity map, in addition to plain kernel map.  This needs to be
- * large enough to allocate page table pages to allocate the rest.
- * Each page can map 2MB.
- */
-#define LEVEL1_IDENT_ENTRIES	(PTRS_PER_PTE * 4)
-static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-#endif
-#ifdef CONFIG_X86_64
-/* l3 pud for userspace vsyscall mapping */
-static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
-#endif /* CONFIG_X86_64 */
-
-/*
- * Note about cr3 (pagetable base) values:
- *
- * xen_cr3 contains the current logical cr3 value; it contains the
- * last set cr3.  This may not be the current effective cr3, because
- * its update may be being lazily deferred.  However, a vcpu looking
- * at its own cr3 can use this value knowing that it everything will
- * be self-consistent.
- *
- * xen_current_cr3 contains the actual vcpu cr3; it is set once the
- * hypercall to set the vcpu cr3 is complete (so it may be a little
- * out of date, but it will never be set early).  If one vcpu is
- * looking at another vcpu's cr3 value, it should use this variable.
- */
-DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
-DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
-
-static phys_addr_t xen_pt_base, xen_pt_size __initdata;
-
-/*
- * Just beyond the highest usermode address.  STACK_TOP_MAX has a
- * redzone above it, so round it up to a PGD boundary.
- */
-#define USER_LIMIT	((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
 
 unsigned long arbitrary_virt_to_mfn(void *vaddr)
 {
···
 }
 EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
 
-void make_lowmem_page_readonly(void *vaddr)
-{
-	pte_t *pte, ptev;
-	unsigned long address = (unsigned long)vaddr;
-	unsigned int level;
-
-	pte = lookup_address(address, &level);
-	if (pte == NULL)
-		return;		/* vaddr missing */
-
-	ptev = pte_wrprotect(*pte);
-
-	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
-		BUG();
-}
-
-void make_lowmem_page_readwrite(void *vaddr)
-{
-	pte_t *pte, ptev;
-	unsigned long address = (unsigned long)vaddr;
-	unsigned int level;
-
-	pte = lookup_address(address, &level);
-	if (pte == NULL)
-		return;		/* vaddr missing */
-
-	ptev = pte_mkwrite(*pte);
-
-	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
-		BUG();
-}
-
-
-static bool xen_page_pinned(void *ptr)
-{
-	struct page *page = virt_to_page(ptr);
-
-	return PagePinned(page);
-}
-
-void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
-{
-	struct multicall_space mcs;
-	struct mmu_update *u;
-
-	trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
-
-	mcs = xen_mc_entry(sizeof(*u));
-	u = mcs.args;
-
-	/* ptep might be kmapped when using 32-bit HIGHPTE */
-	u->ptr = virt_to_machine(ptep).maddr;
-	u->val = pte_val_ma(pteval);
-
-	MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
-EXPORT_SYMBOL_GPL(xen_set_domain_pte);
-
-static void xen_extend_mmu_update(const struct mmu_update *update)
-{
-	struct multicall_space mcs;
-	struct mmu_update *u;
-
-	mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
-
-	if (mcs.mc != NULL) {
-		mcs.mc->args[1]++;
-	} else {
-		mcs = __xen_mc_entry(sizeof(*u));
-		MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
-	}
-
-	u = mcs.args;
-	*u = *update;
-}
-
-static void xen_extend_mmuext_op(const struct mmuext_op *op)
-{
-	struct multicall_space mcs;
-	struct mmuext_op *u;
-
-	mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
-
-	if (mcs.mc != NULL) {
-		mcs.mc->args[1]++;
-	} else {
-		mcs = __xen_mc_entry(sizeof(*u));
-		MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
-	}
-
-	u = mcs.args;
-	*u = *op;
-}
-
-static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
-{
-	struct mmu_update u;
-
-	preempt_disable();
-
-	xen_mc_batch();
-
-	/* ptr may be ioremapped for 64-bit pagetable setup */
-	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
-	u.val = pmd_val_ma(val);
-	xen_extend_mmu_update(&u);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	preempt_enable();
-}
-
-static void xen_set_pmd(pmd_t *ptr, pmd_t val)
-{
-	trace_xen_mmu_set_pmd(ptr, val);
-
-	/* If page is not pinned, we can just update the entry
-	   directly */
-	if (!xen_page_pinned(ptr)) {
-		*ptr = val;
-		return;
-	}
-
-	xen_set_pmd_hyper(ptr, val);
-}
-
-/*
- * Associate a virtual page frame with a given physical page frame
- * and protection flags for that frame.
- */
-void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
-{
-	set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
-}
-
-static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
-{
-	struct mmu_update u;
-
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
-		return false;
-
-	xen_mc_batch();
-
-	u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
-	u.val = pte_val_ma(pteval);
-	xen_extend_mmu_update(&u);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	return true;
-}
-
-static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
-{
-	if (!xen_batched_set_pte(ptep, pteval)) {
-		/*
-		 * Could call native_set_pte() here and trap and
-		 * emulate the PTE write but with 32-bit guests this
-		 * needs two traps (one for each of the two 32-bit
-		 * words in the PTE) so do one hypercall directly
-		 * instead.
-		 */
-		struct mmu_update u;
-
-		u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
-		u.val = pte_val_ma(pteval);
-		HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF);
-	}
-}
-
-static void xen_set_pte(pte_t *ptep, pte_t pteval)
-{
-	trace_xen_mmu_set_pte(ptep, pteval);
-	__xen_set_pte(ptep, pteval);
-}
-
-static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
-		    pte_t *ptep, pte_t pteval)
-{
-	trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
-	__xen_set_pte(ptep, pteval);
-}
-
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
-				 unsigned long addr, pte_t *ptep)
-{
-	/* Just return the pte as-is.  We preserve the bits on commit */
-	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
-	return *ptep;
-}
-
-void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep, pte_t pte)
-{
-	struct mmu_update u;
-
-	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
-	xen_mc_batch();
-
-	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
-	u.val = pte_val_ma(pte);
-	xen_extend_mmu_update(&u);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
-
-/* Assume pteval_t is equivalent to all the other *val_t types. */
-static pteval_t pte_mfn_to_pfn(pteval_t val)
-{
-	if (val & _PAGE_PRESENT) {
-		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
-		unsigned long pfn = mfn_to_pfn(mfn);
-
-		pteval_t flags = val & PTE_FLAGS_MASK;
-		if (unlikely(pfn == ~0))
-			val = flags & ~_PAGE_PRESENT;
-		else
-			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
-	}
-
-	return val;
-}
-
-static pteval_t pte_pfn_to_mfn(pteval_t val)
-{
-	if (val & _PAGE_PRESENT) {
-		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
-		pteval_t flags = val & PTE_FLAGS_MASK;
-		unsigned long mfn;
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap))
-			mfn = __pfn_to_mfn(pfn);
-		else
-			mfn = pfn;
-		/*
-		 * If there's no mfn for the pfn, then just create an
-		 * empty non-present pte.  Unfortunately this loses
-		 * information about the original pfn, so
-		 * pte_mfn_to_pfn is asymmetric.
-		 */
-		if (unlikely(mfn == INVALID_P2M_ENTRY)) {
-			mfn = 0;
-			flags = 0;
-		} else
-			mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
-		val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
-	}
-
-	return val;
-}
-
-__visible pteval_t xen_pte_val(pte_t pte)
-{
-	pteval_t pteval = pte.pte;
-
-	return pte_mfn_to_pfn(pteval);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
-
-__visible pgdval_t xen_pgd_val(pgd_t pgd)
-{
-	return pte_mfn_to_pfn(pgd.pgd);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
-
-__visible pte_t xen_make_pte(pteval_t pte)
-{
-	pte = pte_pfn_to_mfn(pte);
-
-	return native_make_pte(pte);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
-
-__visible pgd_t xen_make_pgd(pgdval_t pgd)
-{
-	pgd = pte_pfn_to_mfn(pgd);
-	return native_make_pgd(pgd);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd);
-
-__visible pmdval_t xen_pmd_val(pmd_t pmd)
-{
-	return pte_mfn_to_pfn(pmd.pmd);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val);
-
-static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
-{
-	struct mmu_update u;
-
-	preempt_disable();
-
-	xen_mc_batch();
-
-	/* ptr may be ioremapped for 64-bit pagetable setup */
-	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
-	u.val = pud_val_ma(val);
-	xen_extend_mmu_update(&u);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	preempt_enable();
-}
-
-static void xen_set_pud(pud_t *ptr, pud_t val)
-{
-	trace_xen_mmu_set_pud(ptr, val);
-
-	/* If page is not pinned, we can just update the entry
-	   directly */
-	if (!xen_page_pinned(ptr)) {
-		*ptr = val;
-		return;
-	}
-
-	xen_set_pud_hyper(ptr, val);
-}
-
-#ifdef CONFIG_X86_PAE
-static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	trace_xen_mmu_set_pte_atomic(ptep, pte);
-	set_64bit((u64 *)ptep, native_pte_val(pte));
-}
-
-static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	trace_xen_mmu_pte_clear(mm, addr, ptep);
-	if (!xen_batched_set_pte(ptep, native_make_pte(0)))
-		native_pte_clear(mm, addr, ptep);
-}
-
-static void xen_pmd_clear(pmd_t *pmdp)
-{
-	trace_xen_mmu_pmd_clear(pmdp);
-	set_pmd(pmdp, __pmd(0));
-}
-#endif	/* CONFIG_X86_PAE */
-
-__visible pmd_t xen_make_pmd(pmdval_t pmd)
-{
-	pmd = pte_pfn_to_mfn(pmd);
-	return native_make_pmd(pmd);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
-
-#if CONFIG_PGTABLE_LEVELS == 4
-__visible pudval_t xen_pud_val(pud_t pud)
-{
-	return pte_mfn_to_pfn(pud.pud);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
-
-__visible pud_t xen_make_pud(pudval_t pud)
-{
-	pud = pte_pfn_to_mfn(pud);
-
-	return native_make_pud(pud);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud);
-
-static pgd_t *xen_get_user_pgd(pgd_t *pgd)
-{
-	pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK);
-	unsigned offset = pgd - pgd_page;
-	pgd_t *user_ptr = NULL;
-
-	if (offset < pgd_index(USER_LIMIT)) {
-		struct page *page = virt_to_page(pgd_page);
-		user_ptr = (pgd_t *)page->private;
-		if (user_ptr)
-			user_ptr += offset;
-	}
-
-	return user_ptr;
-}
-
-static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
-{
-	struct mmu_update u;
-
-	u.ptr = virt_to_machine(ptr).maddr;
-	u.val = p4d_val_ma(val);
-	xen_extend_mmu_update(&u);
-}
-
-/*
- * Raw hypercall-based set_p4d, intended for in early boot before
- * there's a page structure.  This implies:
- *  1. The only existing pagetable is the kernel's
- *  2. It is always pinned
- *  3. It has no user pagetable attached to it
- */
-static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
-{
-	preempt_disable();
-
-	xen_mc_batch();
-
-	__xen_set_p4d_hyper(ptr, val);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	preempt_enable();
-}
-
-static void xen_set_p4d(p4d_t *ptr, p4d_t val)
-{
-	pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr);
-	pgd_t pgd_val;
-
-	trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val);
-
-	/* If page is not pinned, we can just update the entry
-	   directly */
-	if (!xen_page_pinned(ptr)) {
-		*ptr = val;
-		if (user_ptr) {
-			WARN_ON(xen_page_pinned(user_ptr));
-			pgd_val.pgd = p4d_val_ma(val);
-			*user_ptr = pgd_val;
-		}
-		return;
-	}
-
-	/* If it's pinned, then we can at least batch the kernel and
-	   user updates together. */
-	xen_mc_batch();
-
-	__xen_set_p4d_hyper(ptr, val);
-	if (user_ptr)
-		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
-
-static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
-{
-	int i, nr, flush = 0;
-
-	nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD;
-	for (i = 0; i < nr; i++) {
-		if (!pmd_none(pmd[i]))
-			flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE);
-	}
-	return flush;
-}
-
-static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
-{
-	int i, nr, flush = 0;
-
-	nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD;
-	for (i = 0; i < nr; i++) {
-		pmd_t *pmd;
-
-		if (pud_none(pud[i]))
-			continue;
-
-		pmd = pmd_offset(&pud[i], 0);
-		if (PTRS_PER_PMD > 1)
-			flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
-		flush |= xen_pmd_walk(mm, pmd, func,
-				last && i == nr - 1, limit);
-	}
-	return flush;
-}
-
-static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
-{
-	int i, nr, flush = 0;
-
-	nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D;
-	for (i = 0; i < nr; i++) {
-		pud_t *pud;
-
-		if (p4d_none(p4d[i]))
-			continue;
-
-		pud = pud_offset(&p4d[i], 0);
-		if (PTRS_PER_PUD > 1)
-			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
-		flush |= xen_pud_walk(mm, pud, func,
-				last && i == nr - 1, limit);
-	}
-	return flush;
-}
-
-/*
- * (Yet another) pagetable walker.  This one is intended for pinning a
- * pagetable.  This means that it walks a pagetable and calls the
- * callback function on each page it finds making up the page table,
- * at every level.  It walks the entire pagetable, but it only bothers
- * pinning pte pages which are below limit.  In the normal case this
- * will be STACK_TOP_MAX, but at boot we need to pin up to
- * FIXADDR_TOP.
- *
- * For 32-bit the important bit is that we don't pin beyond there,
- * because then we start getting into Xen's ptes.
- *
- * For 64-bit, we must skip the Xen hole in the middle of the address
- * space, just after the big x86-64 virtual hole.
- */
-static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
-			  int (*func)(struct mm_struct *mm, struct page *,
-				      enum pt_level),
-			  unsigned long limit)
-{
-	int i, nr, flush = 0;
-	unsigned hole_low, hole_high;
-
-	/* The limit is the last byte to be touched */
-	limit--;
-	BUG_ON(limit >= FIXADDR_TOP);
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
-	/*
-	 * 64-bit has a great big hole in the middle of the address
-	 * space, which contains the Xen mappings.  On 32-bit these
-	 * will end up making a zero-sized hole and so is a no-op.
-	 */
-	hole_low = pgd_index(USER_LIMIT);
-	hole_high = pgd_index(PAGE_OFFSET);
-
-	nr = pgd_index(limit) + 1;
-	for (i = 0; i < nr; i++) {
-		p4d_t *p4d;
-
-		if (i >= hole_low && i < hole_high)
-			continue;
-
-		if (pgd_none(pgd[i]))
-			continue;
-
-		p4d = p4d_offset(&pgd[i], 0);
-		if (PTRS_PER_P4D > 1)
-			flush |= (*func)(mm, virt_to_page(p4d), PT_P4D);
-		flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
-	}
-
-	/* Do the top level last, so that the callbacks can use it as
-	   a cue to do final things like tlb flushes. */
-	flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
-
-	return flush;
-}
-
-static int xen_pgd_walk(struct mm_struct *mm,
-			int (*func)(struct mm_struct *mm, struct page *,
-				    enum pt_level),
-			unsigned long limit)
-{
-	return __xen_pgd_walk(mm, mm->pgd, func, limit);
-}
-
-/* If we're using split pte locks, then take the page's lock and
-   return a pointer to it.  Otherwise return NULL. */
-static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
-{
-	spinlock_t *ptl = NULL;
-
-#if USE_SPLIT_PTE_PTLOCKS
-	ptl = ptlock_ptr(page);
-	spin_lock_nest_lock(ptl, &mm->page_table_lock);
-#endif
-
-	return ptl;
-}
-
-static void xen_pte_unlock(void *v)
-{
-	spinlock_t *ptl = v;
-	spin_unlock(ptl);
-}
-
-static void xen_do_pin(unsigned level, unsigned long pfn)
-{
-	struct mmuext_op op;
-
-	op.cmd = level;
-	op.arg1.mfn = pfn_to_mfn(pfn);
-
-	xen_extend_mmuext_op(&op);
-}
-
-static int xen_pin_page(struct mm_struct *mm, struct page *page,
-			enum pt_level level)
-{
-	unsigned pgfl = TestSetPagePinned(page);
-	int flush;
-
-	if (pgfl)
-		flush = 0;		/* already pinned */
-	else if (PageHighMem(page))
-		/* kmaps need flushing if we found an unpinned
-		   highpage */
-		flush = 1;
-	else {
-		void *pt = lowmem_page_address(page);
-		unsigned long pfn = page_to_pfn(page);
-		struct multicall_space mcs = __xen_mc_entry(0);
-		spinlock_t *ptl;
-
-		flush = 0;
-
-		/*
-		 * We need to hold the pagetable lock between the time
-		 * we make the pagetable RO and when we actually pin
-		 * it.  If we don't, then other users may come in and
-		 * attempt to update the pagetable by writing it,
-		 * which will fail because the memory is RO but not
-		 * pinned, so Xen won't do the trap'n'emulate.
-		 *
-		 * If we're using split pte locks, we can't hold the
-		 * entire pagetable's worth of locks during the
-		 * traverse, because we may wrap the preempt count (8
-		 * bits).  The solution is to mark RO and pin each PTE
-		 * page while holding the lock.  This means the number
-		 * of locks we end up holding is never more than a
-		 * batch size (~32 entries, at present).
-		 *
-		 * If we're not using split pte locks, we needn't pin
-		 * the PTE pages independently, because we're
-		 * protected by the overall pagetable lock.
-		 */
-		ptl = NULL;
-		if (level == PT_PTE)
-			ptl = xen_pte_lock(page, mm);
-
-		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
-					pfn_pte(pfn, PAGE_KERNEL_RO),
-					level == PT_PGD ? UVMF_TLB_FLUSH : 0);
-
-		if (ptl) {
-			xen_do_pin(MMUEXT_PIN_L1_TABLE, pfn);
-
-			/* Queue a deferred unlock for when this batch
-			   is completed. */
-			xen_mc_callback(xen_pte_unlock, ptl);
-		}
-	}
-
-	return flush;
-}
-
-/* This is called just after a mm has been created, but it has not
-   been used yet.  We need to make sure that its pagetable is all
-   read-only, and can be pinned. */
-static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
-{
-	trace_xen_mmu_pgd_pin(mm, pgd);
-
-	xen_mc_batch();
-
-	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
-		/* re-enable interrupts for flushing */
-		xen_mc_issue(0);
-
-		kmap_flush_unused();
-
-		xen_mc_batch();
-	}
-
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
-		xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
-
-		if (user_pgd) {
-			xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
-			xen_do_pin(MMUEXT_PIN_L4_TABLE,
-				   PFN_DOWN(__pa(user_pgd)));
-		}
-	}
-#else /* CONFIG_X86_32 */
-#ifdef CONFIG_X86_PAE
-	/* Need to make sure unshared kernel PMD is pinnable */
-	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
-		     PT_PMD);
-#endif
-	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
-#endif /* CONFIG_X86_64 */
-	xen_mc_issue(0);
-}
-
-static void xen_pgd_pin(struct mm_struct *mm)
-{
-	__xen_pgd_pin(mm, mm->pgd);
-}
-
-/*
- * On save, we need to pin all pagetables to make sure they get their
- * mfns turned into pfns.  Search the list for any unpinned pgds and pin
- * them (unpinned pgds are not currently in use, probably because the
- * process is under construction or destruction).
- *
- * Expected to be called in stop_machine() ("equivalent to taking
- * every spinlock in the system"), so the locking doesn't really
- * matter all that much.
- */
-void xen_mm_pin_all(void)
-{
-	struct page *page;
-
-	spin_lock(&pgd_lock);
-
-	list_for_each_entry(page, &pgd_list, lru) {
-		if (!PagePinned(page)) {
-			__xen_pgd_pin(&init_mm, (pgd_t *)page_address(page));
-			SetPageSavePinned(page);
-		}
-	}
-
-	spin_unlock(&pgd_lock);
-}
-
-/*
- * The init_mm pagetable is really pinned as soon as its created, but
- * that's before we have page structures to store the bits.  So do all
- * the book-keeping now.
- */
-static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
-				  enum pt_level level)
-{
-	SetPagePinned(page);
-	return 0;
-}
-
-static void __init xen_mark_init_mm_pinned(void)
-{
-	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
-}
-
-static int xen_unpin_page(struct mm_struct *mm, struct page *page,
-			  enum pt_level level)
-{
-	unsigned pgfl = TestClearPagePinned(page);
-
-	if (pgfl && !PageHighMem(page)) {
-		void *pt = lowmem_page_address(page);
-		unsigned long pfn = page_to_pfn(page);
-		spinlock_t *ptl = NULL;
-		struct multicall_space mcs;
-
-		/*
-		 * Do the converse to pin_page.  If we're using split
-		 * pte locks, we must be holding the lock for while
-		 * the pte page is unpinned but still RO to prevent
-		 * concurrent updates from seeing it in this
-		 * partially-pinned state.
-		 */
-		if (level == PT_PTE) {
-			ptl = xen_pte_lock(page, mm);
-
-			if (ptl)
-				xen_do_pin(MMUEXT_UNPIN_TABLE, pfn);
-		}
-
-		mcs = __xen_mc_entry(0);
-
-		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
-					pfn_pte(pfn, PAGE_KERNEL),
-					level == PT_PGD ? UVMF_TLB_FLUSH : 0);
-
-		if (ptl) {
-			/* unlock when batch completed */
-			xen_mc_callback(xen_pte_unlock, ptl);
-		}
-	}
-
-	return 0;		/* never need to flush on unpin */
-}
-
-/* Release a pagetables pages back as normal RW */
-static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
-{
-	trace_xen_mmu_pgd_unpin(mm, pgd);
-
-	xen_mc_batch();
-
-	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
-		if (user_pgd) {
-			xen_do_pin(MMUEXT_UNPIN_TABLE,
-				   PFN_DOWN(__pa(user_pgd)));
-			xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
-		}
-	}
-#endif
-
-#ifdef CONFIG_X86_PAE
-	/* Need to make sure unshared kernel PMD is unpinned */
-	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
-		       PT_PMD);
-#endif
-
-	__xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
-
-	xen_mc_issue(0);
-}
-
-static void xen_pgd_unpin(struct mm_struct *mm)
-{
-	__xen_pgd_unpin(mm, mm->pgd);
-}
-
-/*
- * On resume, undo any pinning done at save, so that the rest of the
- * kernel doesn't see any unexpected pinned pagetables.
- */
-void xen_mm_unpin_all(void)
-{
-	struct page *page;
-
-	spin_lock(&pgd_lock);
-
-	list_for_each_entry(page, &pgd_list, lru) {
-		if (PageSavePinned(page)) {
-			BUG_ON(!PagePinned(page));
-			__xen_pgd_unpin(&init_mm, (pgd_t *)page_address(page));
-			ClearPageSavePinned(page);
-		}
-	}
-
-	spin_unlock(&pgd_lock);
-}
-
-static void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
-{
-	spin_lock(&next->page_table_lock);
-	xen_pgd_pin(next);
-	spin_unlock(&next->page_table_lock);
-}
-
-static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
-{
-	spin_lock(&mm->page_table_lock);
-	xen_pgd_pin(mm);
-	spin_unlock(&mm->page_table_lock);
-}
-
-
-#ifdef CONFIG_SMP
-/* Another cpu may still have their %cr3 pointing at the pagetable, so
-   we need to repoint it somewhere else before we can unpin it. */
-static void drop_other_mm_ref(void *info)
-{
-	struct mm_struct *mm = info;
-	struct mm_struct *active_mm;
-
-	active_mm = this_cpu_read(cpu_tlbstate.active_mm);
-
-	if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
-		leave_mm(smp_processor_id());
-
-	/* If this cpu still has a stale cr3 reference, then make sure
-	   it has been flushed. */
-	if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
-		load_cr3(swapper_pg_dir);
-}
-
-static void xen_drop_mm_ref(struct mm_struct *mm)
-{
-	cpumask_var_t mask;
-	unsigned cpu;
-
-	if (current->active_mm == mm) {
-		if (current->mm == mm)
-			load_cr3(swapper_pg_dir);
-		else
-			leave_mm(smp_processor_id());
-	}
-
-	/* Get the "official" set of cpus referring to our pagetable. */
-	if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
-		for_each_online_cpu(cpu) {
-			if (!cpumask_test_cpu(cpu, mm_cpumask(mm))
-			    && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd))
-				continue;
-			smp_call_function_single(cpu, drop_other_mm_ref, mm, 1);
-		}
-		return;
-	}
-	cpumask_copy(mask, mm_cpumask(mm));
-
-	/* It's possible that a vcpu may have a stale reference to our
-	   cr3, because its in lazy mode, and it hasn't yet flushed
-	   its set of pending hypercalls yet.  In this case, we can
-	   look at its actual current cr3 value, and force it to flush
-	   if needed. */
-	for_each_online_cpu(cpu) {
-		if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
-			cpumask_set_cpu(cpu, mask);
-	}
-
-	if (!cpumask_empty(mask))
-		smp_call_function_many(mask, drop_other_mm_ref, mm, 1);
-	free_cpumask_var(mask);
-}
-#else
-static void xen_drop_mm_ref(struct mm_struct *mm)
-{
-	if (current->active_mm == mm)
-		load_cr3(swapper_pg_dir);
-}
-#endif
-
-/*
- * While a process runs, Xen pins its pagetables, which means that the
- * hypervisor forces it to be read-only, and it controls all updates
- * to it.  This means that all pagetable updates have to go via the
- * hypervisor, which is moderately expensive.
- *
- * Since we're pulling the pagetable down, we switch to use init_mm,
- * unpin old process pagetable and mark it all read-write, which
- * allows further operations on it to be simple memory accesses.
- *
- * The only subtle point is that another CPU may be still using the
- * pagetable because of lazy tlb flushing.  This means we need need to
- * switch all CPUs off this pagetable before we can unpin it.
- */
-static void xen_exit_mmap(struct mm_struct *mm)
-{
-	get_cpu();		/* make sure we don't move around */
-	xen_drop_mm_ref(mm);
-	put_cpu();
-
-	spin_lock(&mm->page_table_lock);
-
-	/* pgd may not be pinned in the error exit path of execve */
-	if (xen_page_pinned(mm->pgd))
-		xen_pgd_unpin(mm);
-
-	spin_unlock(&mm->page_table_lock);
-}
-
-static void xen_post_allocator_init(void);
-
-static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
-	struct mmuext_op op;
-
-	op.cmd = cmd;
-	op.arg1.mfn = pfn_to_mfn(pfn);
-	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-		BUG();
-}
-
-#ifdef CONFIG_X86_64
-static void __init xen_cleanhighmap(unsigned long vaddr,
-				    unsigned long vaddr_end)
-{
-	unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
-	pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
-
-	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
-	 * We include the PMD passed in on _both_ boundaries. */
-	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
-			pmd++, vaddr += PMD_SIZE) {
-		if (pmd_none(*pmd))
-			continue;
-		if (vaddr < (unsigned long) _text || vaddr > kernel_end)
-			set_pmd(pmd, __pmd(0));
-	}
-	/* In case we did something silly, we should crash in this function
-	 * instead of somewhere later and be confusing. */
-	xen_mc_flush();
-}
-
-/*
- * Make a page range writeable and free it.
- */
-static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
-{
-	void *vaddr = __va(paddr);
-	void *vaddr_end = vaddr + size;
-
-	for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
-		make_lowmem_page_readwrite(vaddr);
-
-	memblock_free(paddr, size);
-}
-
-static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
-{
-	unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK;
-
-	if (unpin)
-		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa));
-	ClearPagePinned(virt_to_page(__va(pa)));
-	xen_free_ro_pages(pa, PAGE_SIZE);
-}
-
-static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin)
-{
-	unsigned long pa;
-	pte_t *pte_tbl;
-	int i;
-
-	if (pmd_large(*pmd)) {
-		pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
-		xen_free_ro_pages(pa, PMD_SIZE);
-		return;
-	}
-
-	pte_tbl = pte_offset_kernel(pmd, 0);
-	for (i = 0; i < PTRS_PER_PTE; i++) {
-		if (pte_none(pte_tbl[i]))
-			continue;
-		pa = pte_pfn(pte_tbl[i]) << PAGE_SHIFT;
-		xen_free_ro_pages(pa, PAGE_SIZE);
-	}
-	set_pmd(pmd, __pmd(0));
-	xen_cleanmfnmap_free_pgtbl(pte_tbl, unpin);
-}
-
-static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin)
-{
-	unsigned long pa;
-	pmd_t *pmd_tbl;
-	int i;
-
-	if (pud_large(*pud)) {
-		pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
-		xen_free_ro_pages(pa, PUD_SIZE);
-		return;
-	}
-
-	pmd_tbl = pmd_offset(pud, 0);
-	for (i = 0; i < PTRS_PER_PMD; i++) {
-		if (pmd_none(pmd_tbl[i]))
-			continue;
-		xen_cleanmfnmap_pmd(pmd_tbl + i, unpin);
-	}
-	set_pud(pud, __pud(0));
-	xen_cleanmfnmap_free_pgtbl(pmd_tbl, unpin);
-}
-
-static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin)
-{
-	unsigned long pa;
-	pud_t *pud_tbl;
-	int i;
-
-	if (p4d_large(*p4d)) {
-		pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK;
-		xen_free_ro_pages(pa, P4D_SIZE);
-		return;
-	}
-
-	pud_tbl = pud_offset(p4d, 0);
-	for (i = 0; i < PTRS_PER_PUD; i++) {
-		if (pud_none(pud_tbl[i]))
-			continue;
-		xen_cleanmfnmap_pud(pud_tbl + i, unpin);
-	}
-	set_p4d(p4d, __p4d(0));
-	xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin);
-}
-
-/*
- * Since it is well isolated we can (and since it is perhaps large we should)
- * also free the page tables mapping the initial P->M table.
- */
-static void __init xen_cleanmfnmap(unsigned long vaddr)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	unsigned int i;
-	bool unpin;
-
-	unpin = (vaddr == 2 * PGDIR_SIZE);
-	vaddr &= PMD_MASK;
-	pgd = pgd_offset_k(vaddr);
-	p4d = p4d_offset(pgd, 0);
-	for (i = 0; i < PTRS_PER_P4D; i++) {
-		if (p4d_none(p4d[i]))
-			continue;
-		xen_cleanmfnmap_p4d(p4d + i, unpin);
-	}
-	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-		set_pgd(pgd, __pgd(0));
-		xen_cleanmfnmap_free_pgtbl(p4d, unpin);
-	}
-}
-
-static void __init xen_pagetable_p2m_free(void)
-{
-	unsigned long size;
-	unsigned long addr;
-
-	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
-
-	/* No memory or already called. */
-	if ((unsigned long)xen_p2m_addr == xen_start_info->mfn_list)
-		return;
-
-	/* using __ka address and sticking INVALID_P2M_ENTRY! */
-	memset((void *)xen_start_info->mfn_list, 0xff, size);
-
-	addr = xen_start_info->mfn_list;
-	/*
-	 * We could be in __ka space.
-	 * We roundup to the PMD, which means that if anybody at this stage is
-	 * using the __ka address of xen_start_info or
-	 * xen_start_info->shared_info they are in going to crash. Fortunatly
-	 * we have already revectored in xen_setup_kernel_pagetable and in
-	 * xen_setup_shared_info.
-	 */
-	size = roundup(size, PMD_SIZE);
-
-	if (addr >= __START_KERNEL_map) {
-		xen_cleanhighmap(addr, addr + size);
-		size = PAGE_ALIGN(xen_start_info->nr_pages *
-				  sizeof(unsigned long));
-		memblock_free(__pa(addr), size);
-	} else {
-		xen_cleanmfnmap(addr);
-	}
-}
-
-static void __init xen_pagetable_cleanhighmap(void)
-{
-	unsigned long size;
-	unsigned long addr;
-
-	/* At this stage, cleanup_highmap has already cleaned __ka space
-	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
-	 * the ramdisk). We continue on, erasing PMD entries that point to page
-	 * tables - do note that they are accessible at this stage via __va.
-	 * For good measure we also round up to the PMD - which means that if
-	 * anybody is using __ka address to the initial boot-stack - and try
-	 * to use it - they are going to crash. The xen_start_info has been
-	 * taken care of already in xen_setup_kernel_pagetable. */
-	addr = xen_start_info->pt_base;
-	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
-
-	xen_cleanhighmap(addr, addr + size);
-	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
-#ifdef DEBUG
-	/* This is superfluous and is not necessary, but you know what
-	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
-	 * anything at this stage. */
-	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
-#endif
-}
-#endif
-
-static void __init xen_pagetable_p2m_setup(void)
-{
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	xen_vmalloc_p2m_tree();
-
-#ifdef CONFIG_X86_64
-	xen_pagetable_p2m_free();
-
-	xen_pagetable_cleanhighmap();
-#endif
-	/* And revector! Bye bye old array */
-	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
-}
-
-static void __init xen_pagetable_init(void)
-{
-	paging_init();
-	xen_post_allocator_init();
-
-	xen_pagetable_p2m_setup();
-
-	/* Allocate and initialize top and mid mfn levels for p2m structure */
-	xen_build_mfn_list_list();
-
-	/* Remap memory freed due to conflicts with E820 map */
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		xen_remap_memory();
-
-	xen_setup_shared_info();
-}
-static void xen_write_cr2(unsigned long cr2)
-{
-	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
-}
-
-static unsigned long xen_read_cr2(void)
-{
-	return this_cpu_read(xen_vcpu)->arch.cr2;
-}
-
-unsigned long xen_read_cr2_direct(void)
-{
-	return this_cpu_read(xen_vcpu_info.arch.cr2);
-}
-
 void xen_flush_tlb_all(void)
 {
 	struct mmuext_op *op;
···
 
 	preempt_enable();
 }
-static void xen_flush_tlb(void)
-{
-	struct mmuext_op *op;
-	struct multicall_space mcs;
-
-	trace_xen_mmu_flush_tlb(0);
-
-	preempt_disable();
-
-	mcs = xen_mc_entry(sizeof(*op));
-
-	op = mcs.args;
-	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	preempt_enable();
-}
-
-static void xen_flush_tlb_single(unsigned long addr)
-{
-	struct mmuext_op *op;
-	struct multicall_space mcs;
-
-	trace_xen_mmu_flush_tlb_single(addr);
-
-	preempt_disable();
-
-	mcs = xen_mc_entry(sizeof(*op));
-	op = mcs.args;
-	op->cmd = MMUEXT_INVLPG_LOCAL;
-	op->arg1.linear_addr = addr & PAGE_MASK;
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-	preempt_enable();
-}
-
-static void xen_flush_tlb_others(const struct cpumask *cpus,
-				 struct mm_struct *mm, unsigned long start,
-				 unsigned long end)
-{
-	struct {
-		struct mmuext_op op;
-#ifdef CONFIG_SMP
-		DECLARE_BITMAP(mask, num_processors);
-#else
-		DECLARE_BITMAP(mask, NR_CPUS);
-#endif
-	} *args;
-	struct multicall_space mcs;
-
-	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
-
-	if (cpumask_empty(cpus))
-		return;		/* nothing to do */
-
-	mcs = xen_mc_entry(sizeof(*args));
-	args = mcs.args;
-	args->op.arg2.vcpumask = to_cpumask(args->mask);
-
-	/* Remove us, and any offline CPUS. */
-	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
-
-	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
-		args->op.cmd = MMUEXT_INVLPG_MULTI;
-		args->op.arg1.linear_addr = start;
-	}
-
-	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
-
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
-}
-
-static unsigned long xen_read_cr3(void)
-{
-	return this_cpu_read(xen_cr3);
-}
-
-static void set_current_cr3(void *v)
-{
-	this_cpu_write(xen_current_cr3, (unsigned long)v);
-}
-
-static void __xen_write_cr3(bool kernel, unsigned long cr3)
-{
-	struct mmuext_op op;
-	unsigned long mfn;
-
-	trace_xen_mmu_write_cr3(kernel, cr3);
-
-	if (cr3)
-		mfn = pfn_to_mfn(PFN_DOWN(cr3));
-	else
-		mfn = 0;
-
-	WARN_ON(mfn == 0 && kernel);
-
-	op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
-	op.arg1.mfn = mfn;
-
-	xen_extend_mmuext_op(&op);
-
-	if (kernel) {
-		this_cpu_write(xen_cr3, cr3);
-
-		/* Update xen_current_cr3 once the batch has actually
-		   been submitted. */
-		xen_mc_callback(set_current_cr3, (void *)cr3);
-	}
-}
-static void xen_write_cr3(unsigned long cr3)
-{
-	BUG_ON(preemptible());
-
-	xen_mc_batch();  /* disables interrupts */
-
-	/* Update while interrupts are disabled, so its atomic with
-	   respect to ipis */
-	this_cpu_write(xen_cr3, cr3);
-
-	__xen_write_cr3(true, cr3);
-
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
-		if (user_pgd)
-			__xen_write_cr3(false, __pa(user_pgd));
-		else
-			__xen_write_cr3(false, 0);
-	}
-#endif
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
-}
-
-#ifdef CONFIG_X86_64
-/*
- * At the start of the day - when Xen launches a guest, it has already
- * built pagetables for the guest. We diligently look over them
- * in xen_setup_kernel_pagetable and graft as appropriate them in the
- * init_level4_pgt and its friends. Then when we are happy we load
- * the new init_level4_pgt - and continue on.
- *
- * The generic code starts (start_kernel) and 'init_mem_mapping' sets
- * up the rest of the pagetables. When it has completed it loads the cr3.
- * N.B. that baremetal would start at 'start_kernel' (and the early
- * #PF handler would create bootstrap pagetables) - so we are running
- * with the same assumptions as what to do when write_cr3 is executed
- * at this point.
- *
- * Since there are no user-page tables at all, we have two variants
- * of xen_write_cr3 - the early bootup (this one), and the late one
- * (xen_write_cr3). The reason we have to do that is that in 64-bit
- * the Linux kernel and user-space are both in ring 3 while the
- * hypervisor is in ring 0.
- */
-static void __init xen_write_cr3_init(unsigned long cr3)
-{
-	BUG_ON(preemptible());
-
-	xen_mc_batch();  /* disables interrupts */
-
-	/* Update while interrupts are disabled, so its atomic with
-	   respect to ipis */
-	this_cpu_write(xen_cr3, cr3);
-
-	__xen_write_cr3(true, cr3);
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
-}
-#endif
-
-static int xen_pgd_alloc(struct mm_struct *mm)
-{
-	pgd_t *pgd = mm->pgd;
-	int ret = 0;
-
-	BUG_ON(PagePinned(virt_to_page(pgd)));
-
-#ifdef CONFIG_X86_64
-	{
-		struct page *page = virt_to_page(pgd);
-		pgd_t *user_pgd;
-
-		BUG_ON(page->private != 0);
-
-		ret = -ENOMEM;
-
-		user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		page->private = (unsigned long)user_pgd;
-
-		if (user_pgd != NULL) {
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
-			user_pgd[pgd_index(VSYSCALL_ADDR)] =
-				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
-#endif
-			ret = 0;
-		}
-
-		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
-	}
-#endif
-	return ret;
-}
-
-static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-#ifdef CONFIG_X86_64
-	pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
-	if (user_pgd)
-		free_page((unsigned long)user_pgd);
-#endif
-}
-
-/*
- * Init-time set_pte while constructing initial pagetables, which
- * doesn't allow RO page table pages to be remapped RW.
- *
- * If there is no MFN for this PFN then this page is initially
- * ballooned out so clear the PTE (as in decrease_reservation() in
- * drivers/xen/balloon.c).
- *
- * Many of these PTE updates are done on unpinned and writable pages
- * and doing a hypercall for these is unnecessary and expensive.  At
- * this point it is not possible to tell if a page is pinned or not,
- * so always write the PTE directly and rely on Xen trapping and
- * emulating any updates as necessary.
- */
-__visible pte_t xen_make_pte_init(pteval_t pte)
-{
-#ifdef CONFIG_X86_64
-	unsigned long pfn;
-
-	/*
-	 * Pages belonging to the initial p2m list mapped outside the default
-	 * address range must be mapped read-only. This region contains the
-	 * page tables for mapping the p2m list, too, and page tables MUST be
-	 * mapped read-only.
-	 */
-	pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
-	if (xen_start_info->mfn_list < __START_KERNEL_map &&
-	    pfn >= xen_start_info->first_p2m_pfn &&
-	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
-		pte &= ~_PAGE_RW;
-#endif
-	pte = pte_pfn_to_mfn(pte);
-	return native_make_pte(pte);
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
-
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
-{
-#ifdef CONFIG_X86_32
-	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
-	if (pte_mfn(pte) != INVALID_P2M_ENTRY
-	    && pte_val_ma(*ptep) & _PAGE_PRESENT)
-		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
-			       pte_val_ma(pte));
-#endif
-	native_set_pte(ptep, pte);
-}
-
-/* Early in boot, while setting up the initial pagetable, assume
-   everything is pinned. */
-static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
-{
-#ifdef CONFIG_FLATMEM
-	BUG_ON(mem_map);	/* should only be used early */
-#endif
-	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
-	pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
-}
-
-/* Used for pmd and pud */
-static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
-{
-#ifdef CONFIG_FLATMEM
-	BUG_ON(mem_map);	/* should only be used early */
-#endif
-	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
-}
-
-/* Early release_pte assumes that all pts are pinned, since there's
-   only init_mm and anything attached to that is pinned. */
-static void __init xen_release_pte_init(unsigned long pfn)
-{
-	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
-	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
-}
-
-static void __init xen_release_pmd_init(unsigned long pfn)
-{
-	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
-}
-
-static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
-	struct multicall_space mcs;
-	struct mmuext_op *op;
-
-	mcs = __xen_mc_entry(sizeof(*op));
-	op = mcs.args;
-	op->cmd = cmd;
-	op->arg1.mfn = pfn_to_mfn(pfn);
-
-	MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
-}
-
-static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
-{
-	struct multicall_space mcs;
-	unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
-
-	mcs = __xen_mc_entry(0);
-	MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
-				pfn_pte(pfn, prot), 0);
-}
-
-/* This needs to make sure the new pte page is pinned iff its being
-   attached to a pinned pagetable. */
-static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
-				    unsigned level)
-{
-	bool pinned = PagePinned(virt_to_page(mm->pgd));
-
-	trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
-
-	if (pinned) {
-		struct page *page = pfn_to_page(pfn);
-
-		SetPagePinned(page);
-
-		if (!PageHighMem(page)) {
-			xen_mc_batch();
-
-			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
-
-			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
-				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
-
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-		} else {
-			/* make sure there are no stray mappings of
-			   this page */
-			kmap_flush_unused();
-		}
-	}
-}
-
-static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
-{
-	xen_alloc_ptpage(mm, pfn, PT_PTE);
-}
-
-static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
-{
-	xen_alloc_ptpage(mm, pfn, PT_PMD);
-}
-
-/* This should never happen until we're OK to use struct page */
-static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
-{
-	struct page *page = pfn_to_page(pfn);
-	bool pinned = PagePinned(page);
-
-	trace_xen_mmu_release_ptpage(pfn, level, pinned);
-
-	if (pinned) {
-		if (!PageHighMem(page)) {
-			xen_mc_batch();
-
-			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
-				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
-
-			__set_pfn_prot(pfn, PAGE_KERNEL);
-
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-		}
-		ClearPagePinned(page);
-	}
-}
-
-static void xen_release_pte(unsigned long pfn)
-{
-	xen_release_ptpage(pfn, PT_PTE);
-}
-
-static void xen_release_pmd(unsigned long pfn)
-{
-	xen_release_ptpage(pfn, PT_PMD);
-}
-
-#if CONFIG_PGTABLE_LEVELS >= 4
-static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
-{
-	xen_alloc_ptpage(mm, pfn, PT_PUD);
-}
-
-static void xen_release_pud(unsigned long pfn)
-{
-	xen_release_ptpage(pfn, PT_PUD);
-}
-#endif
-
-void __init xen_reserve_top(void)
-{
-#ifdef CONFIG_X86_32
-	unsigned long top = HYPERVISOR_VIRT_START;
-	struct xen_platform_parameters pp;
-
-	if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
-		top = pp.virt_start;
-
-	reserve_top_address(-top);
-#endif	/* CONFIG_X86_32 */
-}
-
-/*
- * Like __va(), but returns address in the kernel mapping (which is
- * all we have until the physical memory mapping has been set up.
- */
-static void * __init __ka(phys_addr_t paddr)
-{
-#ifdef CONFIG_X86_64
-	return (void *)(paddr + __START_KERNEL_map);
-#else
-	return __va(paddr);
-#endif
-}
-
-/* Convert a machine address to physical address */
-static unsigned long __init m2p(phys_addr_t maddr)
-{
-	phys_addr_t paddr;
-
-	maddr &= PTE_PFN_MASK;
-	paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
-
-	return paddr;
-}
-
-/* Convert a machine address to kernel virtual */
-static void * __init m2v(phys_addr_t maddr)
-{
-	return __ka(m2p(maddr));
-}
-
-/* Set the page permissions on an identity-mapped pages */
-static void __init set_page_prot_flags(void *addr, pgprot_t prot,
-				       unsigned long flags)
-{
-	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
-	pte_t pte = pfn_pte(pfn, prot);
-
-	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
-		BUG();
-}
-static void __init set_page_prot(void *addr, pgprot_t prot)
-{
-	return set_page_prot_flags(addr, prot, UVMF_NONE);
-}
-#ifdef CONFIG_X86_32
-static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
-{
-	unsigned pmdidx, pteidx;
-	unsigned ident_pte;
-	unsigned long pfn;
-
-	level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES,
-				      PAGE_SIZE);
-
-	ident_pte = 0;
-	pfn = 0;
-	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
-		pte_t *pte_page;
-
-		/* Reuse or allocate a page of ptes */
-		if (pmd_present(pmd[pmdidx]))
-			pte_page = m2v(pmd[pmdidx].pmd);
-		else {
-			/* Check for free pte pages */
-			if (ident_pte == LEVEL1_IDENT_ENTRIES)
-				break;
-
-			pte_page = &level1_ident_pgt[ident_pte];
-			ident_pte += PTRS_PER_PTE;
-
-			pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
-		}
-
-		/* Install mappings */
-		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
-			pte_t pte;
-
-			if (pfn > max_pfn_mapped)
-				max_pfn_mapped = pfn;
-
-			if (!pte_none(pte_page[pteidx]))
-				continue;
-
-			pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
-			pte_page[pteidx] = pte;
-		}
-	}
-
-	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
-		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
-
-	set_page_prot(pmd, PAGE_KERNEL_RO);
-}
-#endif
-void __init xen_setup_machphys_mapping(void)
-{
-	struct xen_machphys_mapping mapping;
-
-	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
-		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-		machine_to_phys_nr = mapping.max_mfn + 1;
-	} else {
-		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
-	}
-#ifdef CONFIG_X86_32
-	WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
-		< machine_to_phys_mapping);
-#endif
-}
-
-#ifdef CONFIG_X86_64
-static void __init convert_pfn_mfn(void *v)
-{
-	pte_t *pte = v;
-	int i;
-
-	/* All levels are converted the same way, so just treat them
-	   as ptes. */
-	for (i = 0; i < PTRS_PER_PTE; i++)
-		pte[i] = xen_make_pte(pte[i].pte);
-}
-static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
-				 unsigned long addr)
-{
-	if (*pt_base == PFN_DOWN(__pa(addr))) {
-		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
-		clear_page((void *)addr);
-		(*pt_base)++;
-	}
-	if (*pt_end == PFN_DOWN(__pa(addr))) {
-		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
-		clear_page((void *)addr);
-		(*pt_end)--;
-	}
-}
-/*
- * Set up the initial kernel pagetable.
- *
- * We can construct this by grafting the Xen provided pagetable into
- * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
- * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
- * kernel has a physical mapping to start with - but that's enough to
- * get __va working.  We need to fill in the rest of the physical
- * mapping once some sort of allocator has been set up.
- */
-void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
-{
-	pud_t *l3;
-	pmd_t *l2;
-	unsigned long addr[3];
-	unsigned long pt_base, pt_end;
-	unsigned i;
-
-	/* max_pfn_mapped is the last pfn mapped in the initial memory
-	 * mappings. Considering that on Xen after the kernel mappings we
-	 * have the mappings of some pages that don't exist in pfn space, we
-	 * set max_pfn_mapped to the last real pfn mapped. */
-	if (xen_start_info->mfn_list < __START_KERNEL_map)
-		max_pfn_mapped = xen_start_info->first_p2m_pfn;
-	else
-		max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
-
-	pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
-	pt_end = pt_base + xen_start_info->nr_pt_frames;
-
-	/* Zap identity mapping */
-	init_level4_pgt[0] = __pgd(0);
-
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		/* Pre-constructed entries are in pfn, so convert to mfn */
-		/* L4[272] -> level3_ident_pgt
-		 * L4[511] -> level3_kernel_pgt */
-		convert_pfn_mfn(init_level4_pgt);
-
-		/* L3_i[0] -> level2_ident_pgt */
-		convert_pfn_mfn(level3_ident_pgt);
-		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_k[511] -> level2_fixmap_pgt */
-		convert_pfn_mfn(level3_kernel_pgt);
-
-		/* L3_k[511][506] -> level1_fixmap_pgt */
-		convert_pfn_mfn(level2_fixmap_pgt);
-	}
-	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
-	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
-	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
-
-	addr[0] = (unsigned long)pgd;
-	addr[1] = (unsigned long)l3;
-	addr[2] = (unsigned long)l2;
-	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][510] have entries that point to the same
-	 * L2 (PMD) tables. Meaning that if you modify it in __va space
-	 * it will be also modified in the __ka space! (But if you just
-	 * modify the PMD table to point to other PTE's or none, then you
-	 * are OK - which is what cleanup_highmap does) */
-	copy_page(level2_ident_pgt, l2);
-	/* Graft it onto L4[511][510] */
-	copy_page(level2_kernel_pgt, l2);
-
-	/* Copy the initial P->M table mappings if necessary. */
-	i = pgd_index(xen_start_info->mfn_list);
-	if (i && i < pgd_index(__START_KERNEL_map))
-		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
-
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		/* Make pagetable pieces RO */
-		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
-		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
-		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
-
-		/* Pin down new L4 */
-		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
-				  PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
-		/* Unpin Xen-provided one */
-		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
-		/*
-		 * At this stage there can be no user pgd, and no page
-		 * structure to attach it to, so make sure we just set kernel
-		 * pgd.
-		 */
-		xen_mc_batch();
-		__xen_write_cr3(true, __pa(init_level4_pgt));
-		xen_mc_issue(PARAVIRT_LAZY_CPU);
-	} else
-		native_write_cr3(__pa(init_level4_pgt));
-
-	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
-	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
-	 * the initial domain. For guests using the toolstack, they are in:
-	 * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
-	 * rip out the [L4] (pgd), but for guests we shave off three pages.
-	 */
-	for (i = 0; i < ARRAY_SIZE(addr); i++)
-		check_pt_base(&pt_base, &pt_end, addr[i]);
-
-	/* Our (by three pages) smaller Xen pagetable that we are using */
-	xen_pt_base = PFN_PHYS(pt_base);
-	xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
-	memblock_reserve(xen_pt_base, xen_pt_size);
-
-	/* Revector the xen_start_info */
-	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
-}
-
-/*
- * Read a value from a physical address.
- */
-static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
-{
-	unsigned long *vaddr;
-	unsigned long val;
-
-	vaddr = early_memremap_ro(addr, sizeof(val));
-	val = *vaddr;
-	early_memunmap(vaddr, sizeof(val));
-	return val;
-}
-
-/*
- * Translate a virtual address to a physical one without relying on mapped
- * page tables.
- */
-static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
-{
-	phys_addr_t pa;
-	pgd_t pgd;
-	pud_t pud;
-	pmd_t pmd;
-	pte_t pte;
-
-	pa = read_cr3();
-	pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) *
-						       sizeof(pgd)));
-	if (!pgd_present(pgd))
-		return 0;
-
-	pa = pgd_val(pgd) & PTE_PFN_MASK;
-	pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) *
-						       sizeof(pud)));
-	if (!pud_present(pud))
-		return 0;
-	pa = pud_pfn(pud) << PAGE_SHIFT;
-	if (pud_large(pud))
-		return pa + (vaddr & ~PUD_MASK);
-
-	pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
-						       sizeof(pmd)));
-	if (!pmd_present(pmd))
-		return 0;
-	pa = pmd_pfn(pmd) << PAGE_SHIFT;
-	if (pmd_large(pmd))
-		return pa + (vaddr & ~PMD_MASK);
-
-	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
-						       sizeof(pte)));
-	if (!pte_present(pte))
-		return 0;
-	pa = pte_pfn(pte) << PAGE_SHIFT;
-
-	return pa | (vaddr & ~PAGE_MASK);
-}
-
-/*
- * Find a new area for the hypervisor supplied p2m list and relocate the p2m to
- * this area.
- */
-void __init xen_relocate_p2m(void)
-{
-	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys;
-	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
-	int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d;
-	pte_t *pt;
-	pmd_t *pmd;
-	pud_t *pud;
-	p4d_t *p4d = NULL;
-	pgd_t *pgd;
-	unsigned long *new_p2m;
-	int save_pud;
-
-	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
-	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
-	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
-	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
-	n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT;
-	if (PTRS_PER_P4D > 1)
-		n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
-	else
-		n_p4d = 0;
-	n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d;
-
-	new_area = xen_find_free_area(PFN_PHYS(n_frames));
-	if (!new_area) {
-		xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
-		BUG();
-	}
-
-	/*
-	 * Setup the page tables for addressing the new p2m list.
-	 * We have asked the hypervisor to map the p2m list at the user address
-	 * PUD_SIZE. It may have done so, or it may have used a kernel space
-	 * address depending on the Xen version.
-	 * To avoid any possible virtual address collision, just use
-	 * 2 * PUD_SIZE for the new area.
-	 */
-	p4d_phys = new_area;
-	pud_phys = p4d_phys + PFN_PHYS(n_p4d);
-	pmd_phys = pud_phys + PFN_PHYS(n_pud);
-	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
-	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
-
-	pgd = __va(read_cr3());
-	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
-	idx_p4d = 0;
-	save_pud = n_pud;
-	do {
-		if (n_p4d > 0) {
-			p4d = early_memremap(p4d_phys, PAGE_SIZE);
-			clear_page(p4d);
-			n_pud = min(save_pud, PTRS_PER_P4D);
-		}
-		for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
-			pud = early_memremap(pud_phys, PAGE_SIZE);
-			clear_page(pud);
-			for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
-				 idx_pmd++) {
-				pmd = early_memremap(pmd_phys, PAGE_SIZE);
-				clear_page(pmd);
-				for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
-					 idx_pt++) {
-					pt = early_memremap(pt_phys, PAGE_SIZE);
-					clear_page(pt);
-					for (idx_pte = 0;
-						 idx_pte < min(n_pte, PTRS_PER_PTE);
-						 idx_pte++) {
-						set_pte(pt + idx_pte,
-								pfn_pte(p2m_pfn, PAGE_KERNEL));
-						p2m_pfn++;
-					}
-					n_pte -= PTRS_PER_PTE;
-					early_memunmap(pt, PAGE_SIZE);
-					make_lowmem_page_readonly(__va(pt_phys));
-					pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
-							PFN_DOWN(pt_phys));
-					set_pmd(pmd + idx_pt,
-							__pmd(_PAGE_TABLE | pt_phys));
-					pt_phys += PAGE_SIZE;
-				}
-				n_pt -= PTRS_PER_PMD;
-				early_memunmap(pmd, PAGE_SIZE);
-				make_lowmem_page_readonly(__va(pmd_phys));
-				pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
-						PFN_DOWN(pmd_phys));
-				set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
-				pmd_phys += PAGE_SIZE;
-			}
-			n_pmd -= PTRS_PER_PUD;
-			early_memunmap(pud, PAGE_SIZE);
-			make_lowmem_page_readonly(__va(pud_phys));
-			pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
-			if (n_p4d > 0)
-				set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys));
-			else
-				set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
-			pud_phys += PAGE_SIZE;
-		}
-		if (n_p4d > 0) {
-			save_pud -= PTRS_PER_P4D;
-			early_memunmap(p4d, PAGE_SIZE);
-			make_lowmem_page_readonly(__va(p4d_phys));
-			pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys));
-			set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys));
-			p4d_phys += PAGE_SIZE;
-		}
-	} while (++idx_p4d < n_p4d);
-
-	/* Now copy the old p2m info to the new area. */
-	memcpy(new_p2m, xen_p2m_addr, size);
-	xen_p2m_addr = new_p2m;
-
-	/* Release the old p2m list and set new list info. */
-	p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
-	BUG_ON(!p2m_pfn);
-	p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
-
-	if (xen_start_info->mfn_list < __START_KERNEL_map) {
-		pfn = xen_start_info->first_p2m_pfn;
-		pfn_end = xen_start_info->first_p2m_pfn +
-			  xen_start_info->nr_p2m_frames;
-		set_pgd(pgd + 1, __pgd(0));
-	} else {
-		pfn = p2m_pfn;
-		pfn_end = p2m_pfn_end;
-	}
-
-	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
-	while (pfn < pfn_end) {
-		if (pfn == p2m_pfn) {
-			pfn = p2m_pfn_end;
-			continue;
-		}
-		make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
-		pfn++;
-	}
-
-	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
-	xen_start_info->first_p2m_pfn =  PFN_DOWN(new_area);
-	xen_start_info->nr_p2m_frames = n_frames;
-}
-
-#else	/* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
-static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
-
-static void __init xen_write_cr3_init(unsigned long cr3)
-{
-	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
-
-	BUG_ON(read_cr3() != __pa(initial_page_table));
-	BUG_ON(cr3 != __pa(swapper_pg_dir));
-
-	/*
-	 * We are switching to swapper_pg_dir for the first time (from
-	 * initial_page_table) and therefore need to mark that page
-	 * read-only and then pin it.
-	 *
-	 * Xen disallows sharing of kernel PMDs for PAE
-	 * guests. Therefore we must copy the kernel PMD from
-	 * initial_page_table into a new kernel PMD to be used in
-	 * swapper_pg_dir.
-	 */
-	swapper_kernel_pmd =
-		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-	copy_page(swapper_kernel_pmd, initial_kernel_pmd);
-	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
-		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
-	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
-
-	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
-	xen_write_cr3(cr3);
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
-
-	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
-			  PFN_DOWN(__pa(initial_page_table)));
-	set_page_prot(initial_page_table, PAGE_KERNEL);
-	set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
-
-	pv_mmu_ops.write_cr3 = &xen_write_cr3;
-}
-
-/*
- * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
- * not the first page table in the page table pool.
- * Iterate through the initial page tables to find the real page table base.
- */
-static phys_addr_t xen_find_pt_base(pmd_t *pmd)
-{
-	phys_addr_t pt_base, paddr;
-	unsigned pmdidx;
-
-	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
-
-	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
-		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
-			paddr = m2p(pmd[pmdidx].pmd);
-			pt_base = min(pt_base, paddr);
-		}
-
-	return pt_base;
-}
-
-void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
-{
-	pmd_t *kernel_pmd;
-
-	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-
-	xen_pt_base = xen_find_pt_base(kernel_pmd);
-	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
-
-	initial_kernel_pmd =
-		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-
-	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
-
-	copy_page(initial_kernel_pmd, kernel_pmd);
-
-	xen_map_identity_early(initial_kernel_pmd, max_pfn);
-
-	copy_page(initial_page_table, pgd);
-	initial_page_table[KERNEL_PGD_BOUNDARY] =
-		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
-
-	set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
-	set_page_prot(initial_page_table, PAGE_KERNEL_RO);
-	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
-
-	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
-			  PFN_DOWN(__pa(initial_page_table)));
-	xen_write_cr3(__pa(initial_page_table));
-
-	memblock_reserve(xen_pt_base, xen_pt_size);
-}
-#endif	/* CONFIG_X86_64 */
-
-void __init xen_reserve_special_pages(void)
-{
-	phys_addr_t paddr;
-
-	memblock_reserve(__pa(xen_start_info), PAGE_SIZE);
-	if (xen_start_info->store_mfn) {
-		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn));
-		memblock_reserve(paddr, PAGE_SIZE);
-	}
-	if (!xen_initial_domain()) {
-		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn));
-		memblock_reserve(paddr, PAGE_SIZE);
-	}
-}
-
-void __init xen_pt_check_e820(void)
-{
-	if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
-		xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
-		BUG();
-	}
-}
-
-static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
-
-static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
-{
-	pte_t pte;
-
-	phys >>= PAGE_SHIFT;
-
-	switch (idx) {
-	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-	case FIX_RO_IDT:
-#ifdef CONFIG_X86_32
-	case FIX_WP_TEST:
-# ifdef CONFIG_HIGHMEM
-	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
-# endif
-#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
-	case VSYSCALL_PAGE:
-#endif
-	case FIX_TEXT_POKE0:
-	case FIX_TEXT_POKE1:
-	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
-		/* All local page mappings */
-		pte = pfn_pte(phys, prot);
-		break;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	case FIX_APIC_BASE:	/* maps dummy local APIC */
-		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
-		break;
-#endif
-
-#ifdef CONFIG_X86_IO_APIC
-	case FIX_IO_APIC_BASE_0 ... FIX_IO_APIC_BASE_END:
-		/*
-		 * We just don't map the IO APIC - all access is via
-		 * hypercalls.  Keep the address in the pte for reference.
-		 */
-		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
-		break;
-#endif
-
-	case FIX_PARAVIRT_BOOTMAP:
-		/* This is an MFN, but it isn't an IO mapping from the
-		   IO domain */
-		pte = mfn_pte(phys, prot);
-		break;
-
-	default:
-		/* By default, set_fixmap is used for hardware mappings */
-		pte = mfn_pte(phys, prot);
-		break;
-	}
-
-	__native_set_fixmap(idx, pte);
-
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
-	/* Replicate changes to map the vsyscall page into the user
-	   pagetable vsyscall mapping. */
-	if (idx == VSYSCALL_PAGE) {
-		unsigned long vaddr = __fix_to_virt(idx);
-		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
-	}
-#endif
-}
-
-static void __init xen_post_allocator_init(void)
-{
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	pv_mmu_ops.set_pte = xen_set_pte;
-	pv_mmu_ops.set_pmd = xen_set_pmd;
-	pv_mmu_ops.set_pud = xen_set_pud;
-#if CONFIG_PGTABLE_LEVELS >= 4
-	pv_mmu_ops.set_p4d = xen_set_p4d;
-#endif
-
-	/* This will work as long as patching hasn't happened yet
-	   (which it hasn't) */
-	pv_mmu_ops.alloc_pte = xen_alloc_pte;
-	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
-	pv_mmu_ops.release_pte = xen_release_pte;
-	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if CONFIG_PGTABLE_LEVELS >= 4
-	pv_mmu_ops.alloc_pud = xen_alloc_pud;
-	pv_mmu_ops.release_pud = xen_release_pud;
-#endif
-	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
-
-#ifdef CONFIG_X86_64
-	pv_mmu_ops.write_cr3 = &xen_write_cr3;
-	SetPagePinned(virt_to_page(level3_user_vsyscall));
-#endif
-	xen_mark_init_mm_pinned();
-}
-
-static void xen_leave_lazy_mmu(void)
-{
-	preempt_disable();
-	xen_mc_flush();
-	paravirt_leave_lazy_mmu();
-	preempt_enable();
-}
-
-static const struct pv_mmu_ops xen_mmu_ops __initconst = {
-	.read_cr2 = xen_read_cr2,
-	.write_cr2 = xen_write_cr2,
-
-	.read_cr3 = xen_read_cr3,
-	.write_cr3 = xen_write_cr3_init,
-
-	.flush_tlb_user = xen_flush_tlb,
-	.flush_tlb_kernel = xen_flush_tlb,
-	.flush_tlb_single = xen_flush_tlb_single,
-	.flush_tlb_others = xen_flush_tlb_others,
-
-	.pte_update = paravirt_nop,
-
-	.pgd_alloc = xen_pgd_alloc,
-	.pgd_free = xen_pgd_free,
-
-	.alloc_pte = xen_alloc_pte_init,
-	.release_pte = xen_release_pte_init,
-	.alloc_pmd = xen_alloc_pmd_init,
-	.release_pmd = xen_release_pmd_init,
-
-	.set_pte = xen_set_pte_init,
-	.set_pte_at = xen_set_pte_at,
-	.set_pmd = xen_set_pmd_hyper,
-
-	.ptep_modify_prot_start = __ptep_modify_prot_start,
-	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
-
-	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
-	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
-
-	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
-	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
-
-#ifdef CONFIG_X86_PAE
-	.set_pte_atomic = xen_set_pte_atomic,
-	.pte_clear = xen_pte_clear,
-	.pmd_clear = xen_pmd_clear,
-#endif	/* CONFIG_X86_PAE */
-	.set_pud = xen_set_pud_hyper,
-
-	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
-	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
-
-#if CONFIG_PGTABLE_LEVELS >= 4
-	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
-	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
-	.set_p4d = xen_set_p4d_hyper,
-
-	.alloc_pud = xen_alloc_pmd_init,
-	.release_pud = xen_release_pmd_init,
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
-
-	.activate_mm = xen_activate_mm,
-	.dup_mmap = xen_dup_mmap,
-	.exit_mmap = xen_exit_mmap,
-
-	.lazy_mode = {
-		.enter = paravirt_enter_lazy_mmu,
-		.leave = xen_leave_lazy_mmu,
-		.flush = paravirt_flush_lazy_mmu,
-	},
-
-	.set_fixmap = xen_set_fixmap,
-};
-
-void __init xen_init_mmu_ops(void)
-{
-	x86_init.paging.pagetable_init = xen_pagetable_init;
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	pv_mmu_ops = xen_mmu_ops;
-
-	memset(dummy_mapping, 0xff, PAGE_SIZE);
-}
-
-/* Protected by xen_reservation_lock. */
-#define MAX_CONTIG_ORDER 9 /* 2MB */
-static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
-
-#define VOID_PTE (mfn_pte(0, __pgprot(0)))
-static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
-				unsigned long *in_frames,
-				unsigned long *out_frames)
-{
-	int i;
-	struct multicall_space mcs;
-
-	xen_mc_batch();
-	for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) {
-		mcs = __xen_mc_entry(0);
-
-		if (in_frames)
-			in_frames[i] = virt_to_mfn(vaddr);
-
-		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
-		__set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
-
-		if (out_frames)
-			out_frames[i] = virt_to_pfn(vaddr);
-	}
-	xen_mc_issue(0);
-}
-
-/*
- * Update the pfn-to-mfn mappings for a virtual address range, either to
- * point to an array of mfns, or contiguously from a single starting
- * mfn.
- */
-static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
-				     unsigned long *mfns,
-				     unsigned long first_mfn)
-{
-	unsigned i, limit;
-	unsigned long mfn;
-
-	xen_mc_batch();
-
-	limit = 1u << order;
-	for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) {
-		struct multicall_space mcs;
-		unsigned flags;
-
-		mcs = __xen_mc_entry(0);
-		if (mfns)
-			mfn = mfns[i];
-		else
-			mfn = first_mfn + i;
-
-		if (i < (limit - 1))
-			flags = 0;
-		else {
-			if (order == 0)
-				flags = UVMF_INVLPG | UVMF_ALL;
-			else
-				flags = UVMF_TLB_FLUSH | UVMF_ALL;
-		}
-
-		MULTI_update_va_mapping(mcs.mc, vaddr,
-				mfn_pte(mfn, PAGE_KERNEL), flags);
-
-		set_phys_to_machine(virt_to_pfn(vaddr), mfn);
-	}
-
-	xen_mc_issue(0);
-}
-
-/*
- * Perform the hypercall to exchange a region of our pfns to point to
- * memory with the required contiguous alignment.  Takes the pfns as
- * input, and populates mfns as output.
- *
- * Returns a success code indicating whether the hypervisor was able to
- * satisfy the request or not.
- */
-static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
-			       unsigned long *pfns_in,
-			       unsigned long extents_out,
-			       unsigned int order_out,
-			       unsigned long *mfns_out,
-			       unsigned int address_bits)
-{
-	long rc;
-	int success;
-
-	struct xen_memory_exchange exchange = {
-		.in = {
-			.nr_extents   = extents_in,
-			.extent_order = order_in,
-			.extent_start = pfns_in,
-			.domid        = DOMID_SELF
-		},
-		.out = {
-			.nr_extents   = extents_out,
-			.extent_order = order_out,
-			.extent_start = mfns_out,
-			.address_bits = address_bits,
-			.domid        = DOMID_SELF
-		}
-	};
-
-	BUG_ON(extents_in << order_in != extents_out << order_out);
-
-	rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange);
-	success = (exchange.nr_exchanged == extents_in);
-
-	BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0)));
-	BUG_ON(success && (rc != 0));
-
-	return success;
-}
-
-int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
-				 unsigned int address_bits,
-				 dma_addr_t *dma_handle)
-{
-	unsigned long *in_frames = discontig_frames, out_frame;
-	unsigned long  flags;
-	int            success;
-	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
-
-	/*
-	 * Currently an auto-translated guest will not perform I/O, nor will
-	 * it require PAE page directories below 4GB. Therefore any calls to
-	 * this function are redundant and can be ignored.
-	 */
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
-	if (unlikely(order > MAX_CONTIG_ORDER))
-		return -ENOMEM;
-
-	memset((void *) vstart, 0, PAGE_SIZE << order);
-
-	spin_lock_irqsave(&xen_reservation_lock, flags);
-
-	/* 1. Zap current PTEs, remembering MFNs. */
-	xen_zap_pfn_range(vstart, order, in_frames, NULL);
-
-	/* 2. Get a new contiguous memory extent. */
-	out_frame = virt_to_pfn(vstart);
-	success = xen_exchange_memory(1UL << order, 0, in_frames,
-				      1, order, &out_frame,
-				      address_bits);
-
-	/* 3. Map the new extent in place of old pages. */
-	if (success)
-		xen_remap_exchanged_ptes(vstart, order, NULL, out_frame);
-	else
-		xen_remap_exchanged_ptes(vstart, order, in_frames, 0);
-
-	spin_unlock_irqrestore(&xen_reservation_lock, flags);
-
-	*dma_handle = virt_to_machine(vstart).maddr;
-	return success ? 0 : -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
-
-void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
-{
-	unsigned long *out_frames = discontig_frames, in_frame;
-	unsigned long  flags;
-	int success;
-	unsigned long vstart;
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	if (unlikely(order > MAX_CONTIG_ORDER))
-		return;
-
-	vstart = (unsigned long)phys_to_virt(pstart);
-	memset((void *) vstart, 0, PAGE_SIZE << order);
-
-	spin_lock_irqsave(&xen_reservation_lock, flags);
-
-	/* 1. Find start MFN of contiguous extent. */
-	in_frame = virt_to_mfn(vstart);
-
-	/* 2. Zap current PTEs. */
-	xen_zap_pfn_range(vstart, order, NULL, out_frames);
-
-	/* 3. Do the exchange for non-contiguous MFNs. */
-	success = xen_exchange_memory(1, order, &in_frame, 1UL << order,
-					0, out_frames, 0);
-
-	/* 4. Map new pages in place of old pages. */
-	if (success)
-		xen_remap_exchanged_ptes(vstart, order, out_frames, 0);
-	else
-		xen_remap_exchanged_ptes(vstart, order, NULL, in_frame);
-
-	spin_unlock_irqrestore(&xen_reservation_lock, flags);
-}
-EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
-
-#ifdef CONFIG_XEN_PVHVM
-#ifdef CONFIG_PROC_VMCORE
-/*
- * This function is used in two contexts:
- * - the kdump kernel has to check whether a pfn of the crashed kernel
- *   was a ballooned page. vmcore is using this function to decide
- *   whether to access a pfn of the crashed kernel.
- * - the kexec kernel has to check whether a pfn was ballooned by the
- *   previous kernel. If the pfn is ballooned, handle it properly.
- * Returns 0 if the pfn is not backed by a RAM page, the caller may
- * handle the pfn special in this case.
- */
-static int xen_oldmem_pfn_is_ram(unsigned long pfn)
-{
-	struct xen_hvm_get_mem_type a = {
-		.domid = DOMID_SELF,
-		.pfn = pfn,
-	};
-	int ram;
-
-	if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a))
-		return -ENXIO;
-
-	switch (a.mem_type) {
-		case HVMMEM_mmio_dm:
-			ram = 0;
-			break;
-		case HVMMEM_ram_rw:
-		case HVMMEM_ram_ro:
-		default:
-			ram = 1;
-			break;
-	}
-
-	return ram;
-}
-#endif
-
-static void xen_hvm_exit_mmap(struct mm_struct *mm)
-{
-	struct xen_hvm_pagetable_dying a;
-	int rc;
-
-	a.domid = DOMID_SELF;
-	a.gpa = __pa(mm->pgd);
-	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
-	WARN_ON_ONCE(rc < 0);
-}
-
-static int is_pagetable_dying_supported(void)
-{
-	struct xen_hvm_pagetable_dying a;
-	int rc = 0;
-
-	a.domid = DOMID_SELF;
-	a.gpa = 0x00;
-	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
-	if (rc < 0) {
-		printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n");
-		return 0;
-	}
-	return 1;
-}
-
-void __init xen_hvm_init_mmu_ops(void)
-{
-	if (is_pagetable_dying_supported())
-		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
-#ifdef CONFIG_PROC_VMCORE
-	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
-#endif
-}
-#endif
 
 #define REMAP_BATCH_SIZE 16
 
···
 	return do_remap_gfn(vma, addr, gfn, nr, err_ptr, prot, domid, pages);
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array);
-
 
 /* Returns: 0 success */
 int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,

arch/x86/xen/mmu_hvm.c

···
+#include <linux/types.h>
+#include <linux/crash_dump.h>
+
+#include <xen/interface/xen.h>
+#include <xen/hvm.h>
+
+#include "mmu.h"
+
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * This function is used in two contexts:
+ * - the kdump kernel has to check whether a pfn of the crashed kernel
+ *   was a ballooned page. vmcore is using this function to decide
+ *   whether to access a pfn of the crashed kernel.
+ * - the kexec kernel has to check whether a pfn was ballooned by the
+ *   previous kernel. If the pfn is ballooned, handle it properly.
+ * Returns 0 if the pfn is not backed by a RAM page, the caller may
+ * handle the pfn special in this case.
+ */
+static int xen_oldmem_pfn_is_ram(unsigned long pfn)
+{
+	struct xen_hvm_get_mem_type a = {
+		.domid = DOMID_SELF,
+		.pfn = pfn,
+	};
+	int ram;
+
+	if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a))
+		return -ENXIO;
+
+	switch (a.mem_type) {
+	case HVMMEM_mmio_dm:
+		ram = 0;
+		break;
+	case HVMMEM_ram_rw:
+	case HVMMEM_ram_ro:
+	default:
+		ram = 1;
+		break;
+	}
+
+	return ram;
+}
+#endif
+
+static void xen_hvm_exit_mmap(struct mm_struct *mm)
+{
+	struct xen_hvm_pagetable_dying a;
+	int rc;
+
+	a.domid = DOMID_SELF;
+	a.gpa = __pa(mm->pgd);
+	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
+	WARN_ON_ONCE(rc < 0);
+}
+
+static int is_pagetable_dying_supported(void)
+{
+	struct xen_hvm_pagetable_dying a;
+	int rc = 0;
+
+	a.domid = DOMID_SELF;
+	a.gpa = 0x00;
+	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
+	if (rc < 0) {
+		printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n");
+		return 0;
+	}
+	return 1;
+}
+
+void __init xen_hvm_init_mmu_ops(void)
+{
+	if (is_pagetable_dying_supported())
+		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+#ifdef CONFIG_PROC_VMCORE
+	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+#endif
+}

arch/x86/xen/mmu_pv.c

···
+/*
+ * Xen mmu operations
+ *
+ * This file contains the various mmu fetch and update operations.
+ * The most important job they must perform is the mapping between the
+ * domain's pfn and the overall machine mfns.
+ *
+ * Xen allows guests to directly update the pagetable, in a controlled
+ * fashion.  In other words, the guest modifies the same pagetable
+ * that the CPU actually uses, which eliminates the overhead of having
+ * a separate shadow pagetable.
+ *
+ * In order to allow this, it falls on the guest domain to map its
+ * notion of a "physical" pfn - which is just a domain-local linear
+ * address - into a real "machine address" which the CPU's MMU can
+ * use.
+ *
+ * A pgd_t/pmd_t/pte_t will typically contain an mfn, and so can be
+ * inserted directly into the pagetable.  When creating a new
+ * pte/pmd/pgd, it converts the passed pfn into an mfn.  Conversely,
+ * when reading the content back with __(pgd|pmd|pte)_val, it converts
+ * the mfn back into a pfn.
+ *
+ * The other constraint is that all pages which 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 a
+ * pagetable page RW, and will disallow using any writable page as a
+ * pagetable.
+ *
+ * Naively, when loading %cr3 with the base of a new pagetable, Xen
+ * would need to validate the whole pagetable before going on.
+ * Naturally, this is quite slow.  The solution is to "pin" a
+ * pagetable, which enforces all the constraints on the pagetable even
+ * when it is not actively in use.  This menas that Xen can be assured
+ * that it is still valid when you do load it into %cr3, and doesn't
+ * need to revalidate it.
+ *
+ * Jeremy Fitzhardinge <[e-mail]>, XenSource Inc, 2007
+ */
+#include <linux/sched/mm.h>
+#include <linux/highmem.h>
+#include <linux/debugfs.h>
+#include <linux/bug.h>
+#include <linux/vmalloc.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/memblock.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
+#include <trace/events/xen.h>
+
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+#include <asm/mmu_context.h>
+#include <asm/setup.h>
+#include <asm/paravirt.h>
+#include <asm/e820/api.h>
+#include <asm/linkage.h>
+#include <asm/page.h>
+#include <asm/init.h>
+#include <asm/pat.h>
+#include <asm/smp.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
+#include <xen/page.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/hvm/hvm_op.h>
+#include <xen/interface/version.h>
+#include <xen/interface/memory.h>
+#include <xen/hvc-console.h>
+
+#include "multicalls.h"
+#include "mmu.h"
+#include "debugfs.h"
+
+#ifdef CONFIG_X86_32
+/*
+ * Identity map, in addition to plain kernel map.  This needs to be
+ * large enough to allocate page table pages to allocate the rest.
+ * Each page can map 2MB.
+ */
+#define LEVEL1_IDENT_ENTRIES	(PTRS_PER_PTE * 4)
+static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
+#endif
+#ifdef CONFIG_X86_64
+/* l3 pud for userspace vsyscall mapping */
+static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Note about cr3 (pagetable base) values:
+ *
+ * xen_cr3 contains the current logical cr3 value; it contains the
+ * last set cr3.  This may not be the current effective cr3, because
+ * its update may be being lazily deferred.  However, a vcpu looking
+ * at its own cr3 can use this value knowing that it everything will
+ * be self-consistent.
+ *
+ * xen_current_cr3 contains the actual vcpu cr3; it is set once the
+ * hypercall to set the vcpu cr3 is complete (so it may be a little
+ * out of date, but it will never be set early).  If one vcpu is
+ * looking at another vcpu's cr3 value, it should use this variable.
+ */
+DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
+DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
+
+static phys_addr_t xen_pt_base, xen_pt_size __initdata;
+
+/*
+ * Just beyond the highest usermode address.  STACK_TOP_MAX has a
+ * redzone above it, so round it up to a PGD boundary.
+ */
+#define USER_LIMIT	((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
+
+void make_lowmem_page_readonly(void *vaddr)
+{
+	pte_t *pte, ptev;
+	unsigned long address = (unsigned long)vaddr;
+	unsigned int level;
+
+	pte = lookup_address(address, &level);
+	if (pte == NULL)
+		return;		/* vaddr missing */
+
+	ptev = pte_wrprotect(*pte);
+
+	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
+		BUG();
+}
+
+void make_lowmem_page_readwrite(void *vaddr)
+{
+	pte_t *pte, ptev;
+	unsigned long address = (unsigned long)vaddr;
+	unsigned int level;
+
+	pte = lookup_address(address, &level);
+	if (pte == NULL)
+		return;		/* vaddr missing */
+
+	ptev = pte_mkwrite(*pte);
+
+	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
+		BUG();
+}
+
+
+static bool xen_page_pinned(void *ptr)
+{
+	struct page *page = virt_to_page(ptr);
+
+	return PagePinned(page);
+}
+
+void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
+{
+	struct multicall_space mcs;
+	struct mmu_update *u;
+
+	trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
+
+	mcs = xen_mc_entry(sizeof(*u));
+	u = mcs.args;
+
+	/* ptep might be kmapped when using 32-bit HIGHPTE */
+	u->ptr = virt_to_machine(ptep).maddr;
+	u->val = pte_val_ma(pteval);
+
+	MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+EXPORT_SYMBOL_GPL(xen_set_domain_pte);
+
+static void xen_extend_mmu_update(const struct mmu_update *update)
+{
+	struct multicall_space mcs;
+	struct mmu_update *u;
+
+	mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
+
+	if (mcs.mc != NULL) {
+		mcs.mc->args[1]++;
+	} else {
+		mcs = __xen_mc_entry(sizeof(*u));
+		MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+	}
+
+	u = mcs.args;
+	*u = *update;
+}
+
+static void xen_extend_mmuext_op(const struct mmuext_op *op)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *u;
+
+	mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
+
+	if (mcs.mc != NULL) {
+		mcs.mc->args[1]++;
+	} else {
+		mcs = __xen_mc_entry(sizeof(*u));
+		MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+	}
+
+	u = mcs.args;
+	*u = *op;
+}
+
+static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+{
+	struct mmu_update u;
+
+	preempt_disable();
+
+	xen_mc_batch();
+
+	/* ptr may be ioremapped for 64-bit pagetable setup */
+	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
+	u.val = pmd_val_ma(val);
+	xen_extend_mmu_update(&u);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+static void xen_set_pmd(pmd_t *ptr, pmd_t val)
+{
+	trace_xen_mmu_set_pmd(ptr, val);
+
+	/* If page is not pinned, we can just update the entry
+	   directly */
+	if (!xen_page_pinned(ptr)) {
+		*ptr = val;
+		return;
+	}
+
+	xen_set_pmd_hyper(ptr, val);
+}
+
+/*
+ * Associate a virtual page frame with a given physical page frame
+ * and protection flags for that frame.
+ */
+void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
+{
+	set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
+}
+
+static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
+{
+	struct mmu_update u;
+
+	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+		return false;
+
+	xen_mc_batch();
+
+	u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+	u.val = pte_val_ma(pteval);
+	xen_extend_mmu_update(&u);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	return true;
+}
+
+static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+	if (!xen_batched_set_pte(ptep, pteval)) {
+		/*
+		 * Could call native_set_pte() here and trap and
+		 * emulate the PTE write but with 32-bit guests this
+		 * needs two traps (one for each of the two 32-bit
+		 * words in the PTE) so do one hypercall directly
+		 * instead.
+		 */
+		struct mmu_update u;
+
+		u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+		u.val = pte_val_ma(pteval);
+		HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF);
+	}
+}
+
+static void xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+	trace_xen_mmu_set_pte(ptep, pteval);
+	__xen_set_pte(ptep, pteval);
+}
+
+static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
+		    pte_t *ptep, pte_t pteval)
+{
+	trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
+	__xen_set_pte(ptep, pteval);
+}
+
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+				 unsigned long addr, pte_t *ptep)
+{
+	/* Just return the pte as-is.  We preserve the bits on commit */
+	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
+	return *ptep;
+}
+
+void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep, pte_t pte)
+{
+	struct mmu_update u;
+
+	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
+	xen_mc_batch();
+
+	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+	u.val = pte_val_ma(pte);
+	xen_extend_mmu_update(&u);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long pfn = mfn_to_pfn(mfn);
+
+		pteval_t flags = val & PTE_FLAGS_MASK;
+		if (unlikely(pfn == ~0))
+			val = flags & ~_PAGE_PRESENT;
+		else
+			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & PTE_FLAGS_MASK;
+		unsigned long mfn;
+
+		if (!xen_feature(XENFEAT_auto_translated_physmap))
+			mfn = __pfn_to_mfn(pfn);
+		else
+			mfn = pfn;
+		/*
+		 * If there's no mfn for the pfn, then just create an
+		 * empty non-present pte.  Unfortunately this loses
+		 * information about the original pfn, so
+		 * pte_mfn_to_pfn is asymmetric.
+		 */
+		if (unlikely(mfn == INVALID_P2M_ENTRY)) {
+			mfn = 0;
+			flags = 0;
+		} else
+			mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
+		val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+__visible pteval_t xen_pte_val(pte_t pte)
+{
+	pteval_t pteval = pte.pte;
+
+	return pte_mfn_to_pfn(pteval);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
+
+__visible pgdval_t xen_pgd_val(pgd_t pgd)
+{
+	return pte_mfn_to_pfn(pgd.pgd);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
+
+__visible pte_t xen_make_pte(pteval_t pte)
+{
+	pte = pte_pfn_to_mfn(pte);
+
+	return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
+
+__visible pgd_t xen_make_pgd(pgdval_t pgd)
+{
+	pgd = pte_pfn_to_mfn(pgd);
+	return native_make_pgd(pgd);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd);
+
+__visible pmdval_t xen_pmd_val(pmd_t pmd)
+{
+	return pte_mfn_to_pfn(pmd.pmd);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val);
+
+static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
+{
+	struct mmu_update u;
+
+	preempt_disable();
+
+	xen_mc_batch();
+
+	/* ptr may be ioremapped for 64-bit pagetable setup */
+	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
+	u.val = pud_val_ma(val);
+	xen_extend_mmu_update(&u);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+static void xen_set_pud(pud_t *ptr, pud_t val)
+{
+	trace_xen_mmu_set_pud(ptr, val);
+
+	/* If page is not pinned, we can just update the entry
+	   directly */
+	if (!xen_page_pinned(ptr)) {
+		*ptr = val;
+		return;
+	}
+
+	xen_set_pud_hyper(ptr, val);
+}
+
+#ifdef CONFIG_X86_PAE
+static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	trace_xen_mmu_set_pte_atomic(ptep, pte);
+	set_64bit((u64 *)ptep, native_pte_val(pte));
+}
+
+static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	trace_xen_mmu_pte_clear(mm, addr, ptep);
+	if (!xen_batched_set_pte(ptep, native_make_pte(0)))
+		native_pte_clear(mm, addr, ptep);
+}
+
+static void xen_pmd_clear(pmd_t *pmdp)
+{
+	trace_xen_mmu_pmd_clear(pmdp);
+	set_pmd(pmdp, __pmd(0));
+}
+#endif	/* CONFIG_X86_PAE */
+
+__visible pmd_t xen_make_pmd(pmdval_t pmd)
+{
+	pmd = pte_pfn_to_mfn(pmd);
+	return native_make_pmd(pmd);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
+
+#if CONFIG_PGTABLE_LEVELS == 4
+__visible pudval_t xen_pud_val(pud_t pud)
+{
+	return pte_mfn_to_pfn(pud.pud);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
+
+__visible pud_t xen_make_pud(pudval_t pud)
+{
+	pud = pte_pfn_to_mfn(pud);
+
+	return native_make_pud(pud);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud);
+
+static pgd_t *xen_get_user_pgd(pgd_t *pgd)
+{
+	pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK);
+	unsigned offset = pgd - pgd_page;
+	pgd_t *user_ptr = NULL;
+
+	if (offset < pgd_index(USER_LIMIT)) {
+		struct page *page = virt_to_page(pgd_page);
+		user_ptr = (pgd_t *)page->private;
+		if (user_ptr)
+			user_ptr += offset;
+	}
+
+	return user_ptr;
+}
+
+static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
+{
+	struct mmu_update u;
+
+	u.ptr = virt_to_machine(ptr).maddr;
+	u.val = p4d_val_ma(val);
+	xen_extend_mmu_update(&u);
+}
+
+/*
+ * Raw hypercall-based set_p4d, intended for in early boot before
+ * there's a page structure.  This implies:
+ *  1. The only existing pagetable is the kernel's
+ *  2. It is always pinned
+ *  3. It has no user pagetable attached to it
+ */
+static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
+{
+	preempt_disable();
+
+	xen_mc_batch();
+
+	__xen_set_p4d_hyper(ptr, val);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+static void xen_set_p4d(p4d_t *ptr, p4d_t val)
+{
+	pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr);
+	pgd_t pgd_val;
+
+	trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val);
+
+	/* If page is not pinned, we can just update the entry
+	   directly */
+	if (!xen_page_pinned(ptr)) {
+		*ptr = val;
+		if (user_ptr) {
+			WARN_ON(xen_page_pinned(user_ptr));
+			pgd_val.pgd = p4d_val_ma(val);
+			*user_ptr = pgd_val;
+		}
+		return;
+	}
+
+	/* If it's pinned, then we can at least batch the kernel and
+	   user updates together. */
+	xen_mc_batch();
+
+	__xen_set_p4d_hyper(ptr, val);
+	if (user_ptr)
+		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+
+static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD;
+	for (i = 0; i < nr; i++) {
+		if (!pmd_none(pmd[i]))
+			flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE);
+	}
+	return flush;
+}
+
+static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD;
+	for (i = 0; i < nr; i++) {
+		pmd_t *pmd;
+
+		if (pud_none(pud[i]))
+			continue;
+
+		pmd = pmd_offset(&pud[i], 0);
+		if (PTRS_PER_PMD > 1)
+			flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
+		flush |= xen_pmd_walk(mm, pmd, func,
+				last && i == nr - 1, limit);
+	}
+	return flush;
+}
+
+static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
+		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
+		bool last, unsigned long limit)
+{
+	int i, nr, flush = 0;
+
+	nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D;
+	for (i = 0; i < nr; i++) {
+		pud_t *pud;
+
+		if (p4d_none(p4d[i]))
+			continue;
+
+		pud = pud_offset(&p4d[i], 0);
+		if (PTRS_PER_PUD > 1)
+			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
+		flush |= xen_pud_walk(mm, pud, func,
+				last && i == nr - 1, limit);
+	}
+	return flush;
+}
+
+/*
+ * (Yet another) pagetable walker.  This one is intended for pinning a
+ * pagetable.  This means that it walks a pagetable and calls the
+ * callback function on each page it finds making up the page table,
+ * at every level.  It walks the entire pagetable, but it only bothers
+ * pinning pte pages which are below limit.  In the normal case this
+ * will be STACK_TOP_MAX, but at boot we need to pin up to
+ * FIXADDR_TOP.
+ *
+ * For 32-bit the important bit is that we don't pin beyond there,
+ * because then we start getting into Xen's ptes.
+ *
+ * For 64-bit, we must skip the Xen hole in the middle of the address
+ * space, just after the big x86-64 virtual hole.
+ */
+static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
+			  int (*func)(struct mm_struct *mm, struct page *,
+				      enum pt_level),
+			  unsigned long limit)
+{
+	int i, nr, flush = 0;
+	unsigned hole_low, hole_high;
+
+	/* The limit is the last byte to be touched */
+	limit--;
+	BUG_ON(limit >= FIXADDR_TOP);
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
+	/*
+	 * 64-bit has a great big hole in the middle of the address
+	 * space, which contains the Xen mappings.  On 32-bit these
+	 * will end up making a zero-sized hole and so is a no-op.
+	 */
+	hole_low = pgd_index(USER_LIMIT);
+	hole_high = pgd_index(PAGE_OFFSET);
+
+	nr = pgd_index(limit) + 1;
+	for (i = 0; i < nr; i++) {
+		p4d_t *p4d;
+
+		if (i >= hole_low && i < hole_high)
+			continue;
+
+		if (pgd_none(pgd[i]))
+			continue;
+
+		p4d = p4d_offset(&pgd[i], 0);
+		if (PTRS_PER_P4D > 1)
+			flush |= (*func)(mm, virt_to_page(p4d), PT_P4D);
+		flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
+	}
+
+	/* Do the top level last, so that the callbacks can use it as
+	   a cue to do final things like tlb flushes. */
+	flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
+
+	return flush;
+}
+
+static int xen_pgd_walk(struct mm_struct *mm,
+			int (*func)(struct mm_struct *mm, struct page *,
+				    enum pt_level),
+			unsigned long limit)
+{
+	return __xen_pgd_walk(mm, mm->pgd, func, limit);
+}
+
+/* If we're using split pte locks, then take the page's lock and
+   return a pointer to it.  Otherwise return NULL. */
+static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
+{
+	spinlock_t *ptl = NULL;
+
+#if USE_SPLIT_PTE_PTLOCKS
+	ptl = ptlock_ptr(page);
+	spin_lock_nest_lock(ptl, &mm->page_table_lock);
+#endif
+
+	return ptl;
+}
+
+static void xen_pte_unlock(void *v)
+{
+	spinlock_t *ptl = v;
+	spin_unlock(ptl);
+}
+
+static void xen_do_pin(unsigned level, unsigned long pfn)
+{
+	struct mmuext_op op;
+
+	op.cmd = level;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+
+	xen_extend_mmuext_op(&op);
+}
+
+static int xen_pin_page(struct mm_struct *mm, struct page *page,
+			enum pt_level level)
+{
+	unsigned pgfl = TestSetPagePinned(page);
+	int flush;
+
+	if (pgfl)
+		flush = 0;		/* already pinned */
+	else if (PageHighMem(page))
+		/* kmaps need flushing if we found an unpinned
+		   highpage */
+		flush = 1;
+	else {
+		void *pt = lowmem_page_address(page);
+		unsigned long pfn = page_to_pfn(page);
+		struct multicall_space mcs = __xen_mc_entry(0);
+		spinlock_t *ptl;
+
+		flush = 0;
+
+		/*
+		 * We need to hold the pagetable lock between the time
+		 * we make the pagetable RO and when we actually pin
+		 * it.  If we don't, then other users may come in and
+		 * attempt to update the pagetable by writing it,
+		 * which will fail because the memory is RO but not
+		 * pinned, so Xen won't do the trap'n'emulate.
+		 *
+		 * If we're using split pte locks, we can't hold the
+		 * entire pagetable's worth of locks during the
+		 * traverse, because we may wrap the preempt count (8
+		 * bits).  The solution is to mark RO and pin each PTE
+		 * page while holding the lock.  This means the number
+		 * of locks we end up holding is never more than a
+		 * batch size (~32 entries, at present).
+		 *
+		 * If we're not using split pte locks, we needn't pin
+		 * the PTE pages independently, because we're
+		 * protected by the overall pagetable lock.
+		 */
+		ptl = NULL;
+		if (level == PT_PTE)
+			ptl = xen_pte_lock(page, mm);
+
+		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
+					pfn_pte(pfn, PAGE_KERNEL_RO),
+					level == PT_PGD ? UVMF_TLB_FLUSH : 0);
+
+		if (ptl) {
+			xen_do_pin(MMUEXT_PIN_L1_TABLE, pfn);
+
+			/* Queue a deferred unlock for when this batch
+			   is completed. */
+			xen_mc_callback(xen_pte_unlock, ptl);
+		}
+	}
+
+	return flush;
+}
+
+/* This is called just after a mm has been created, but it has not
+   been used yet.  We need to make sure that its pagetable is all
+   read-only, and can be pinned. */
+static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
+{
+	trace_xen_mmu_pgd_pin(mm, pgd);
+
+	xen_mc_batch();
+
+	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
+		/* re-enable interrupts for flushing */
+		xen_mc_issue(0);
+
+		kmap_flush_unused();
+
+		xen_mc_batch();
+	}
+
+#ifdef CONFIG_X86_64
+	{
+		pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+		xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
+
+		if (user_pgd) {
+			xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
+			xen_do_pin(MMUEXT_PIN_L4_TABLE,
+				   PFN_DOWN(__pa(user_pgd)));
+		}
+	}
+#else /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_PAE
+	/* Need to make sure unshared kernel PMD is pinnable */
+	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
+		     PT_PMD);
+#endif
+	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
+#endif /* CONFIG_X86_64 */
+	xen_mc_issue(0);
+}
+
+static void xen_pgd_pin(struct mm_struct *mm)
+{
+	__xen_pgd_pin(mm, mm->pgd);
+}
+
+/*
+ * On save, we need to pin all pagetables to make sure they get their
+ * mfns turned into pfns.  Search the list for any unpinned pgds and pin
+ * them (unpinned pgds are not currently in use, probably because the
+ * process is under construction or destruction).
+ *
+ * Expected to be called in stop_machine() ("equivalent to taking
+ * every spinlock in the system"), so the locking doesn't really
+ * matter all that much.
+ */
+void xen_mm_pin_all(void)
+{
+	struct page *page;
+
+	spin_lock(&pgd_lock);
+
+	list_for_each_entry(page, &pgd_list, lru) {
+		if (!PagePinned(page)) {
+			__xen_pgd_pin(&init_mm, (pgd_t *)page_address(page));
+			SetPageSavePinned(page);
+		}
+	}
+
+	spin_unlock(&pgd_lock);
+}
+
+/*
+ * The init_mm pagetable is really pinned as soon as its created, but
+ * that's before we have page structures to store the bits.  So do all
+ * the book-keeping now.
+ */
+static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
+				  enum pt_level level)
+{
+	SetPagePinned(page);
+	return 0;
+}
+
+static void __init xen_mark_init_mm_pinned(void)
+{
+	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
+}
+
+static int xen_unpin_page(struct mm_struct *mm, struct page *page,
+			  enum pt_level level)
+{
+	unsigned pgfl = TestClearPagePinned(page);
+
+	if (pgfl && !PageHighMem(page)) {
+		void *pt = lowmem_page_address(page);
+		unsigned long pfn = page_to_pfn(page);
+		spinlock_t *ptl = NULL;
+		struct multicall_space mcs;
+
+		/*
+		 * Do the converse to pin_page.  If we're using split
+		 * pte locks, we must be holding the lock for while
+		 * the pte page is unpinned but still RO to prevent
+		 * concurrent updates from seeing it in this
+		 * partially-pinned state.
+		 */
+		if (level == PT_PTE) {
+			ptl = xen_pte_lock(page, mm);
+
+			if (ptl)
+				xen_do_pin(MMUEXT_UNPIN_TABLE, pfn);
+		}
+
+		mcs = __xen_mc_entry(0);
+
+		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
+					pfn_pte(pfn, PAGE_KERNEL),
+					level == PT_PGD ? UVMF_TLB_FLUSH : 0);
+
+		if (ptl) {
+			/* unlock when batch completed */
+			xen_mc_callback(xen_pte_unlock, ptl);
+		}
+	}
+
+	return 0;		/* never need to flush on unpin */
+}
+
+/* Release a pagetables pages back as normal RW */
+static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
+{
+	trace_xen_mmu_pgd_unpin(mm, pgd);
+
+	xen_mc_batch();
+
+	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+#ifdef CONFIG_X86_64
+	{
+		pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+		if (user_pgd) {
+			xen_do_pin(MMUEXT_UNPIN_TABLE,
+				   PFN_DOWN(__pa(user_pgd)));
+			xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
+		}
+	}
+#endif
+
+#ifdef CONFIG_X86_PAE
+	/* Need to make sure unshared kernel PMD is unpinned */
+	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
+		       PT_PMD);
+#endif
+
+	__xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
+
+	xen_mc_issue(0);
+}
+
+static void xen_pgd_unpin(struct mm_struct *mm)
+{
+	__xen_pgd_unpin(mm, mm->pgd);
+}
+
+/*
+ * On resume, undo any pinning done at save, so that the rest of the
+ * kernel doesn't see any unexpected pinned pagetables.
+ */
+void xen_mm_unpin_all(void)
+{
+	struct page *page;
+
+	spin_lock(&pgd_lock);
+
+	list_for_each_entry(page, &pgd_list, lru) {
+		if (PageSavePinned(page)) {
+			BUG_ON(!PagePinned(page));
+			__xen_pgd_unpin(&init_mm, (pgd_t *)page_address(page));
+			ClearPageSavePinned(page);
+		}
+	}
+
+	spin_unlock(&pgd_lock);
+}
+
+static void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
+{
+	spin_lock(&next->page_table_lock);
+	xen_pgd_pin(next);
+	spin_unlock(&next->page_table_lock);
+}
+
+static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	spin_lock(&mm->page_table_lock);
+	xen_pgd_pin(mm);
+	spin_unlock(&mm->page_table_lock);
+}
+
+
+#ifdef CONFIG_SMP
+/* Another cpu may still have their %cr3 pointing at the pagetable, so
+   we need to repoint it somewhere else before we can unpin it. */
+static void drop_other_mm_ref(void *info)
+{
+	struct mm_struct *mm = info;
+	struct mm_struct *active_mm;
+
+	active_mm = this_cpu_read(cpu_tlbstate.active_mm);
+
+	if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
+		leave_mm(smp_processor_id());
+
+	/* If this cpu still has a stale cr3 reference, then make sure
+	   it has been flushed. */
+	if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
+		load_cr3(swapper_pg_dir);
+}
+
+static void xen_drop_mm_ref(struct mm_struct *mm)
+{
+	cpumask_var_t mask;
+	unsigned cpu;
+
+	if (current->active_mm == mm) {
+		if (current->mm == mm)
+			load_cr3(swapper_pg_dir);
+		else
+			leave_mm(smp_processor_id());
+	}
+
+	/* Get the "official" set of cpus referring to our pagetable. */
+	if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
+		for_each_online_cpu(cpu) {
+			if (!cpumask_test_cpu(cpu, mm_cpumask(mm))
+			    && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd))
+				continue;
+			smp_call_function_single(cpu, drop_other_mm_ref, mm, 1);
+		}
+		return;
+	}
+	cpumask_copy(mask, mm_cpumask(mm));
+
+	/* It's possible that a vcpu may have a stale reference to our
+	   cr3, because its in lazy mode, and it hasn't yet flushed
+	   its set of pending hypercalls yet.  In this case, we can
+	   look at its actual current cr3 value, and force it to flush
+	   if needed. */
+	for_each_online_cpu(cpu) {
+		if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
+			cpumask_set_cpu(cpu, mask);
+	}
+
+	if (!cpumask_empty(mask))
+		smp_call_function_many(mask, drop_other_mm_ref, mm, 1);
+	free_cpumask_var(mask);
+}
+#else
+static void xen_drop_mm_ref(struct mm_struct *mm)
+{
+	if (current->active_mm == mm)
+		load_cr3(swapper_pg_dir);
+}
+#endif
+
+/*
+ * While a process runs, Xen pins its pagetables, which means that the
+ * hypervisor forces it to be read-only, and it controls all updates
+ * to it.  This means that all pagetable updates have to go via the
+ * hypervisor, which is moderately expensive.
+ *
+ * Since we're pulling the pagetable down, we switch to use init_mm,
+ * unpin old process pagetable and mark it all read-write, which
+ * allows further operations on it to be simple memory accesses.
+ *
+ * The only subtle point is that another CPU may be still using the
+ * pagetable because of lazy tlb flushing.  This means we need need to
+ * switch all CPUs off this pagetable before we can unpin it.
+ */
+static void xen_exit_mmap(struct mm_struct *mm)
+{
+	get_cpu();		/* make sure we don't move around */
+	xen_drop_mm_ref(mm);
+	put_cpu();
+
+	spin_lock(&mm->page_table_lock);
+
+	/* pgd may not be pinned in the error exit path of execve */
+	if (xen_page_pinned(mm->pgd))
+		xen_pgd_unpin(mm);
+
+	spin_unlock(&mm->page_table_lock);
+}
+
+static void xen_post_allocator_init(void);
+
+static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct mmuext_op op;
+
+	op.cmd = cmd;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+		BUG();
+}
+
+#ifdef CONFIG_X86_64
+static void __init xen_cleanhighmap(unsigned long vaddr,
+				    unsigned long vaddr_end)
+{
+	unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+	pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
+
+	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
+	 * We include the PMD passed in on _both_ boundaries. */
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
+			pmd++, vaddr += PMD_SIZE) {
+		if (pmd_none(*pmd))
+			continue;
+		if (vaddr < (unsigned long) _text || vaddr > kernel_end)
+			set_pmd(pmd, __pmd(0));
+	}
+	/* In case we did something silly, we should crash in this function
+	 * instead of somewhere later and be confusing. */
+	xen_mc_flush();
+}
+
+/*
+ * Make a page range writeable and free it.
+ */
+static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
+{
+	void *vaddr = __va(paddr);
+	void *vaddr_end = vaddr + size;
+
+	for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
+		make_lowmem_page_readwrite(vaddr);
+
+	memblock_free(paddr, size);
+}
+
+static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
+{
+	unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK;
+
+	if (unpin)
+		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa));
+	ClearPagePinned(virt_to_page(__va(pa)));
+	xen_free_ro_pages(pa, PAGE_SIZE);
+}
+
+static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin)
+{
+	unsigned long pa;
+	pte_t *pte_tbl;
+	int i;
+
+	if (pmd_large(*pmd)) {
+		pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, PMD_SIZE);
+		return;
+	}
+
+	pte_tbl = pte_offset_kernel(pmd, 0);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		if (pte_none(pte_tbl[i]))
+			continue;
+		pa = pte_pfn(pte_tbl[i]) << PAGE_SHIFT;
+		xen_free_ro_pages(pa, PAGE_SIZE);
+	}
+	set_pmd(pmd, __pmd(0));
+	xen_cleanmfnmap_free_pgtbl(pte_tbl, unpin);
+}
+
+static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin)
+{
+	unsigned long pa;
+	pmd_t *pmd_tbl;
+	int i;
+
+	if (pud_large(*pud)) {
+		pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, PUD_SIZE);
+		return;
+	}
+
+	pmd_tbl = pmd_offset(pud, 0);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (pmd_none(pmd_tbl[i]))
+			continue;
+		xen_cleanmfnmap_pmd(pmd_tbl + i, unpin);
+	}
+	set_pud(pud, __pud(0));
+	xen_cleanmfnmap_free_pgtbl(pmd_tbl, unpin);
+}
+
+static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin)
+{
+	unsigned long pa;
+	pud_t *pud_tbl;
+	int i;
+
+	if (p4d_large(*p4d)) {
+		pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK;
+		xen_free_ro_pages(pa, P4D_SIZE);
+		return;
+	}
+
+	pud_tbl = pud_offset(p4d, 0);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (pud_none(pud_tbl[i]))
+			continue;
+		xen_cleanmfnmap_pud(pud_tbl + i, unpin);
+	}
+	set_p4d(p4d, __p4d(0));
+	xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin);
+}
+
+/*
+ * Since it is well isolated we can (and since it is perhaps large we should)
+ * also free the page tables mapping the initial P->M table.
+ */
+static void __init xen_cleanmfnmap(unsigned long vaddr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	unsigned int i;
+	bool unpin;
+
+	unpin = (vaddr == 2 * PGDIR_SIZE);
+	vaddr &= PMD_MASK;
+	pgd = pgd_offset_k(vaddr);
+	p4d = p4d_offset(pgd, 0);
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		if (p4d_none(p4d[i]))
+			continue;
+		xen_cleanmfnmap_p4d(p4d + i, unpin);
+	}
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		set_pgd(pgd, __pgd(0));
+		xen_cleanmfnmap_free_pgtbl(p4d, unpin);
+	}
+}
+
+static void __init xen_pagetable_p2m_free(void)
+{
+	unsigned long size;
+	unsigned long addr;
+
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+	/* No memory or already called. */
+	if ((unsigned long)xen_p2m_addr == xen_start_info->mfn_list)
+		return;
+
+	/* using __ka address and sticking INVALID_P2M_ENTRY! */
+	memset((void *)xen_start_info->mfn_list, 0xff, size);
+
+	addr = xen_start_info->mfn_list;
+	/*
+	 * We could be in __ka space.
+	 * We roundup to the PMD, which means that if anybody at this stage is
+	 * using the __ka address of xen_start_info or
+	 * xen_start_info->shared_info they are in going to crash. Fortunatly
+	 * we have already revectored in xen_setup_kernel_pagetable and in
+	 * xen_setup_shared_info.
+	 */
+	size = roundup(size, PMD_SIZE);
+
+	if (addr >= __START_KERNEL_map) {
+		xen_cleanhighmap(addr, addr + size);
+		size = PAGE_ALIGN(xen_start_info->nr_pages *
+				  sizeof(unsigned long));
+		memblock_free(__pa(addr), size);
+	} else {
+		xen_cleanmfnmap(addr);
+	}
+}
+
+static void __init xen_pagetable_cleanhighmap(void)
+{
+	unsigned long size;
+	unsigned long addr;
+
+	/* At this stage, cleanup_highmap has already cleaned __ka space
+	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
+	 * the ramdisk). We continue on, erasing PMD entries that point to page
+	 * tables - do note that they are accessible at this stage via __va.
+	 * For good measure we also round up to the PMD - which means that if
+	 * anybody is using __ka address to the initial boot-stack - and try
+	 * to use it - they are going to crash. The xen_start_info has been
+	 * taken care of already in xen_setup_kernel_pagetable. */
+	addr = xen_start_info->pt_base;
+	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+
+	xen_cleanhighmap(addr, addr + size);
+	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
+#ifdef DEBUG
+	/* This is superfluous and is not necessary, but you know what
+	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
+	 * anything at this stage. */
+	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
+#endif
+}
+#endif
+
+static void __init xen_pagetable_p2m_setup(void)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	xen_vmalloc_p2m_tree();
+
+#ifdef CONFIG_X86_64
+	xen_pagetable_p2m_free();
+
+	xen_pagetable_cleanhighmap();
+#endif
+	/* And revector! Bye bye old array */
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+}
+
+static void __init xen_pagetable_init(void)
+{
+	paging_init();
+	xen_post_allocator_init();
+
+	xen_pagetable_p2m_setup();
+
+	/* Allocate and initialize top and mid mfn levels for p2m structure */
+	xen_build_mfn_list_list();
+
+	/* Remap memory freed due to conflicts with E820 map */
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		xen_remap_memory();
+
+	xen_setup_shared_info();
+}
+static void xen_write_cr2(unsigned long cr2)
+{
+	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
+}
+
+static unsigned long xen_read_cr2(void)
+{
+	return this_cpu_read(xen_vcpu)->arch.cr2;
+}
+
+unsigned long xen_read_cr2_direct(void)
+{
+	return this_cpu_read(xen_vcpu_info.arch.cr2);
+}
+
+static void xen_flush_tlb(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+static void xen_flush_tlb_single(unsigned long addr)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_single(addr);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+	op = mcs.args;
+	op->cmd = MMUEXT_INVLPG_LOCAL;
+	op->arg1.linear_addr = addr & PAGE_MASK;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
+
+static void xen_flush_tlb_others(const struct cpumask *cpus,
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long end)
+{
+	struct {
+		struct mmuext_op op;
+#ifdef CONFIG_SMP
+		DECLARE_BITMAP(mask, num_processors);
+#else
+		DECLARE_BITMAP(mask, NR_CPUS);
+#endif
+	} *args;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
+
+	if (cpumask_empty(cpus))
+		return;		/* nothing to do */
+
+	mcs = xen_mc_entry(sizeof(*args));
+	args = mcs.args;
+	args->op.arg2.vcpumask = to_cpumask(args->mask);
+
+	/* Remove us, and any offline CPUS. */
+	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
+
+	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+		args->op.cmd = MMUEXT_INVLPG_MULTI;
+		args->op.arg1.linear_addr = start;
+	}
+
+	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
+static unsigned long xen_read_cr3(void)
+{
+	return this_cpu_read(xen_cr3);
+}
+
+static void set_current_cr3(void *v)
+{
+	this_cpu_write(xen_current_cr3, (unsigned long)v);
+}
+
+static void __xen_write_cr3(bool kernel, unsigned long cr3)
+{
+	struct mmuext_op op;
+	unsigned long mfn;
+
+	trace_xen_mmu_write_cr3(kernel, cr3);
+
+	if (cr3)
+		mfn = pfn_to_mfn(PFN_DOWN(cr3));
+	else
+		mfn = 0;
+
+	WARN_ON(mfn == 0 && kernel);
+
+	op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+	op.arg1.mfn = mfn;
+
+	xen_extend_mmuext_op(&op);
+
+	if (kernel) {
+		this_cpu_write(xen_cr3, cr3);
+
+		/* Update xen_current_cr3 once the batch has actually
+		   been submitted. */
+		xen_mc_callback(set_current_cr3, (void *)cr3);
+	}
+}
+static void xen_write_cr3(unsigned long cr3)
+{
+	BUG_ON(preemptible());
+
+	xen_mc_batch();  /* disables interrupts */
+
+	/* Update while interrupts are disabled, so its atomic with
+	   respect to ipis */
+	this_cpu_write(xen_cr3, cr3);
+
+	__xen_write_cr3(true, cr3);
+
+#ifdef CONFIG_X86_64
+	{
+		pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+		if (user_pgd)
+			__xen_write_cr3(false, __pa(user_pgd));
+		else
+			__xen_write_cr3(false, 0);
+	}
+#endif
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+}
+
+#ifdef CONFIG_X86_64
+/*
+ * At the start of the day - when Xen launches a guest, it has already
+ * built pagetables for the guest. We diligently look over them
+ * in xen_setup_kernel_pagetable and graft as appropriate them in the
+ * init_level4_pgt and its friends. Then when we are happy we load
+ * the new init_level4_pgt - and continue on.
+ *
+ * The generic code starts (start_kernel) and 'init_mem_mapping' sets
+ * up the rest of the pagetables. When it has completed it loads the cr3.
+ * N.B. that baremetal would start at 'start_kernel' (and the early
+ * #PF handler would create bootstrap pagetables) - so we are running
+ * with the same assumptions as what to do when write_cr3 is executed
+ * at this point.
+ *
+ * Since there are no user-page tables at all, we have two variants
+ * of xen_write_cr3 - the early bootup (this one), and the late one
+ * (xen_write_cr3). The reason we have to do that is that in 64-bit
+ * the Linux kernel and user-space are both in ring 3 while the
+ * hypervisor is in ring 0.
+ */
+static void __init xen_write_cr3_init(unsigned long cr3)
+{
+	BUG_ON(preemptible());
+
+	xen_mc_batch();  /* disables interrupts */
+
+	/* Update while interrupts are disabled, so its atomic with
+	   respect to ipis */
+	this_cpu_write(xen_cr3, cr3);
+
+	__xen_write_cr3(true, cr3);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+}
+#endif
+
+static int xen_pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = mm->pgd;
+	int ret = 0;
+
+	BUG_ON(PagePinned(virt_to_page(pgd)));
+
+#ifdef CONFIG_X86_64
+	{
+		struct page *page = virt_to_page(pgd);
+		pgd_t *user_pgd;
+
+		BUG_ON(page->private != 0);
+
+		ret = -ENOMEM;
+
+		user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		page->private = (unsigned long)user_pgd;
+
+		if (user_pgd != NULL) {
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+			user_pgd[pgd_index(VSYSCALL_ADDR)] =
+				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+#endif
+			ret = 0;
+		}
+
+		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+	}
+#endif
+	return ret;
+}
+
+static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifdef CONFIG_X86_64
+	pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+	if (user_pgd)
+		free_page((unsigned long)user_pgd);
+#endif
+}
+
+/*
+ * Init-time set_pte while constructing initial pagetables, which
+ * doesn't allow RO page table pages to be remapped RW.
+ *
+ * If there is no MFN for this PFN then this page is initially
+ * ballooned out so clear the PTE (as in decrease_reservation() in
+ * drivers/xen/balloon.c).
+ *
+ * Many of these PTE updates are done on unpinned and writable pages
+ * and doing a hypercall for these is unnecessary and expensive.  At
+ * this point it is not possible to tell if a page is pinned or not,
+ * so always write the PTE directly and rely on Xen trapping and
+ * emulating any updates as necessary.
+ */
+__visible pte_t xen_make_pte_init(pteval_t pte)
+{
+#ifdef CONFIG_X86_64
+	unsigned long pfn;
+
+	/*
+	 * Pages belonging to the initial p2m list mapped outside the default
+	 * address range must be mapped read-only. This region contains the
+	 * page tables for mapping the p2m list, too, and page tables MUST be
+	 * mapped read-only.
+	 */
+	pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+	if (xen_start_info->mfn_list < __START_KERNEL_map &&
+	    pfn >= xen_start_info->first_p2m_pfn &&
+	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+		pte &= ~_PAGE_RW;
+#endif
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+#ifdef CONFIG_X86_32
+	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
+	if (pte_mfn(pte) != INVALID_P2M_ENTRY
+	    && pte_val_ma(*ptep) & _PAGE_PRESENT)
+		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+			       pte_val_ma(pte));
+#endif
+	native_set_pte(ptep, pte);
+}
+
+/* Early in boot, while setting up the initial pagetable, assume
+   everything is pinned. */
+static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
+{
+#ifdef CONFIG_FLATMEM
+	BUG_ON(mem_map);	/* should only be used early */
+#endif
+	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
+	pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+}
+
+/* Used for pmd and pud */
+static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
+{
+#ifdef CONFIG_FLATMEM
+	BUG_ON(mem_map);	/* should only be used early */
+#endif
+	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
+}
+
+/* Early release_pte assumes that all pts are pinned, since there's
+   only init_mm and anything attached to that is pinned. */
+static void __init xen_release_pte_init(unsigned long pfn)
+{
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+}
+
+static void __init xen_release_pmd_init(unsigned long pfn)
+{
+	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+}
+
+static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *op;
+
+	mcs = __xen_mc_entry(sizeof(*op));
+	op = mcs.args;
+	op->cmd = cmd;
+	op->arg1.mfn = pfn_to_mfn(pfn);
+
+	MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+}
+
+static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	struct multicall_space mcs;
+	unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
+
+	mcs = __xen_mc_entry(0);
+	MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
+				pfn_pte(pfn, prot), 0);
+}
+
+/* This needs to make sure the new pte page is pinned iff its being
+   attached to a pinned pagetable. */
+static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
+				    unsigned level)
+{
+	bool pinned = PagePinned(virt_to_page(mm->pgd));
+
+	trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
+
+	if (pinned) {
+		struct page *page = pfn_to_page(pfn);
+
+		SetPagePinned(page);
+
+		if (!PageHighMem(page)) {
+			xen_mc_batch();
+
+			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
+
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+		} else {
+			/* make sure there are no stray mappings of
+			   this page */
+			kmap_flush_unused();
+		}
+	}
+}
+
+static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
+{
+	xen_alloc_ptpage(mm, pfn, PT_PTE);
+}
+
+static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
+{
+	xen_alloc_ptpage(mm, pfn, PT_PMD);
+}
+
+/* This should never happen until we're OK to use struct page */
+static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
+{
+	struct page *page = pfn_to_page(pfn);
+	bool pinned = PagePinned(page);
+
+	trace_xen_mmu_release_ptpage(pfn, level, pinned);
+
+	if (pinned) {
+		if (!PageHighMem(page)) {
+			xen_mc_batch();
+
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+
+			__set_pfn_prot(pfn, PAGE_KERNEL);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+		}
+		ClearPagePinned(page);
+	}
+}
+
+static void xen_release_pte(unsigned long pfn)
+{
+	xen_release_ptpage(pfn, PT_PTE);
+}
+
+static void xen_release_pmd(unsigned long pfn)
+{
+	xen_release_ptpage(pfn, PT_PMD);
+}
+
+#if CONFIG_PGTABLE_LEVELS >= 4
+static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
+{
+	xen_alloc_ptpage(mm, pfn, PT_PUD);
+}
+
+static void xen_release_pud(unsigned long pfn)
+{
+	xen_release_ptpage(pfn, PT_PUD);
+}
+#endif
+
+void __init xen_reserve_top(void)
+{
+#ifdef CONFIG_X86_32
+	unsigned long top = HYPERVISOR_VIRT_START;
+	struct xen_platform_parameters pp;
+
+	if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
+		top = pp.virt_start;
+
+	reserve_top_address(-top);
+#endif	/* CONFIG_X86_32 */
+}
+
+/*
+ * Like __va(), but returns address in the kernel mapping (which is
+ * all we have until the physical memory mapping has been set up.
+ */
+static void * __init __ka(phys_addr_t paddr)
+{
+#ifdef CONFIG_X86_64
+	return (void *)(paddr + __START_KERNEL_map);
+#else
+	return __va(paddr);
+#endif
+}
+
+/* Convert a machine address to physical address */
+static unsigned long __init m2p(phys_addr_t maddr)
+{
+	phys_addr_t paddr;
+
+	maddr &= PTE_PFN_MASK;
+	paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
+
+	return paddr;
+}
+
+/* Convert a machine address to kernel virtual */
+static void * __init m2v(phys_addr_t maddr)
+{
+	return __ka(m2p(maddr));
+}
+
+/* Set the page permissions on an identity-mapped pages */
+static void __init set_page_prot_flags(void *addr, pgprot_t prot,
+				       unsigned long flags)
+{
+	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+	pte_t pte = pfn_pte(pfn, prot);
+
+	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
+		BUG();
+}
+static void __init set_page_prot(void *addr, pgprot_t prot)
+{
+	return set_page_prot_flags(addr, prot, UVMF_NONE);
+}
+#ifdef CONFIG_X86_32
+static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+{
+	unsigned pmdidx, pteidx;
+	unsigned ident_pte;
+	unsigned long pfn;
+
+	level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES,
+				      PAGE_SIZE);
+
+	ident_pte = 0;
+	pfn = 0;
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+		pte_t *pte_page;
+
+		/* Reuse or allocate a page of ptes */
+		if (pmd_present(pmd[pmdidx]))
+			pte_page = m2v(pmd[pmdidx].pmd);
+		else {
+			/* Check for free pte pages */
+			if (ident_pte == LEVEL1_IDENT_ENTRIES)
+				break;
+
+			pte_page = &level1_ident_pgt[ident_pte];
+			ident_pte += PTRS_PER_PTE;
+
+			pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
+		}
+
+		/* Install mappings */
+		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+			pte_t pte;
+
+			if (pfn > max_pfn_mapped)
+				max_pfn_mapped = pfn;
+
+			if (!pte_none(pte_page[pteidx]))
+				continue;
+
+			pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
+			pte_page[pteidx] = pte;
+		}
+	}
+
+	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
+
+	set_page_prot(pmd, PAGE_KERNEL_RO);
+}
+#endif
+void __init xen_setup_machphys_mapping(void)
+{
+	struct xen_machphys_mapping mapping;
+
+	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
+		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
+		machine_to_phys_nr = mapping.max_mfn + 1;
+	} else {
+		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
+	}
+#ifdef CONFIG_X86_32
+	WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
+		< machine_to_phys_mapping);
+#endif
+}
+
+#ifdef CONFIG_X86_64
+static void __init convert_pfn_mfn(void *v)
+{
+	pte_t *pte = v;
+	int i;
+
+	/* All levels are converted the same way, so just treat them
+	   as ptes. */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		pte[i] = xen_make_pte(pte[i].pte);
+}
+static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
+				 unsigned long addr)
+{
+	if (*pt_base == PFN_DOWN(__pa(addr))) {
+		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
+		clear_page((void *)addr);
+		(*pt_base)++;
+	}
+	if (*pt_end == PFN_DOWN(__pa(addr))) {
+		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
+		clear_page((void *)addr);
+		(*pt_end)--;
+	}
+}
+/*
+ * Set up the initial kernel pagetable.
+ *
+ * We can construct this by grafting the Xen provided pagetable into
+ * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
+ * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
+ * kernel has a physical mapping to start with - but that's enough to
+ * get __va working.  We need to fill in the rest of the physical
+ * mapping once some sort of allocator has been set up.
+ */
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+	pud_t *l3;
+	pmd_t *l2;
+	unsigned long addr[3];
+	unsigned long pt_base, pt_end;
+	unsigned i;
+
+	/* max_pfn_mapped is the last pfn mapped in the initial memory
+	 * mappings. Considering that on Xen after the kernel mappings we
+	 * have the mappings of some pages that don't exist in pfn space, we
+	 * set max_pfn_mapped to the last real pfn mapped. */
+	if (xen_start_info->mfn_list < __START_KERNEL_map)
+		max_pfn_mapped = xen_start_info->first_p2m_pfn;
+	else
+		max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+
+	pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
+	pt_end = pt_base + xen_start_info->nr_pt_frames;
+
+	/* Zap identity mapping */
+	init_level4_pgt[0] = __pgd(0);
+
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		/* Pre-constructed entries are in pfn, so convert to mfn */
+		/* L4[272] -> level3_ident_pgt
+		 * L4[511] -> level3_kernel_pgt */
+		convert_pfn_mfn(init_level4_pgt);
+
+		/* L3_i[0] -> level2_ident_pgt */
+		convert_pfn_mfn(level3_ident_pgt);
+		/* L3_k[510] -> level2_kernel_pgt
+		 * L3_k[511] -> level2_fixmap_pgt */
+		convert_pfn_mfn(level3_kernel_pgt);
+
+		/* L3_k[511][506] -> level1_fixmap_pgt */
+		convert_pfn_mfn(level2_fixmap_pgt);
+	}
+	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
+	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
+	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
+
+	addr[0] = (unsigned long)pgd;
+	addr[1] = (unsigned long)l3;
+	addr[2] = (unsigned long)l2;
+	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
+	 * Both L4[272][0] and L4[511][510] have entries that point to the same
+	 * L2 (PMD) tables. Meaning that if you modify it in __va space
+	 * it will be also modified in the __ka space! (But if you just
+	 * modify the PMD table to point to other PTE's or none, then you
+	 * are OK - which is what cleanup_highmap does) */
+	copy_page(level2_ident_pgt, l2);
+	/* Graft it onto L4[511][510] */
+	copy_page(level2_kernel_pgt, l2);
+
+	/* Copy the initial P->M table mappings if necessary. */
+	i = pgd_index(xen_start_info->mfn_list);
+	if (i && i < pgd_index(__START_KERNEL_map))
+		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
+
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		/* Make pagetable pieces RO */
+		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+		/* Pin down new L4 */
+		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+				  PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+		/* Unpin Xen-provided one */
+		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+		/*
+		 * At this stage there can be no user pgd, and no page
+		 * structure to attach it to, so make sure we just set kernel
+		 * pgd.
+		 */
+		xen_mc_batch();
+		__xen_write_cr3(true, __pa(init_level4_pgt));
+		xen_mc_issue(PARAVIRT_LAZY_CPU);
+	} else
+		native_write_cr3(__pa(init_level4_pgt));
+
+	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
+	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
+	 * the initial domain. For guests using the toolstack, they are in:
+	 * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
+	 * rip out the [L4] (pgd), but for guests we shave off three pages.
+	 */
+	for (i = 0; i < ARRAY_SIZE(addr); i++)
+		check_pt_base(&pt_base, &pt_end, addr[i]);
+
+	/* Our (by three pages) smaller Xen pagetable that we are using */
+	xen_pt_base = PFN_PHYS(pt_base);
+	xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
+	memblock_reserve(xen_pt_base, xen_pt_size);
+
+	/* Revector the xen_start_info */
+	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
+}
+
+/*
+ * Read a value from a physical address.
+ */
+static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
+{
+	unsigned long *vaddr;
+	unsigned long val;
+
+	vaddr = early_memremap_ro(addr, sizeof(val));
+	val = *vaddr;
+	early_memunmap(vaddr, sizeof(val));
+	return val;
+}
+
+/*
+ * Translate a virtual address to a physical one without relying on mapped
+ * page tables.
+ */
+static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
+{
+	phys_addr_t pa;
+	pgd_t pgd;
+	pud_t pud;
+	pmd_t pmd;
+	pte_t pte;
+
+	pa = read_cr3();
+	pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) *
+						       sizeof(pgd)));
+	if (!pgd_present(pgd))
+		return 0;
+
+	pa = pgd_val(pgd) & PTE_PFN_MASK;
+	pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) *
+						       sizeof(pud)));
+	if (!pud_present(pud))
+		return 0;
+	pa = pud_pfn(pud) << PAGE_SHIFT;
+	if (pud_large(pud))
+		return pa + (vaddr & ~PUD_MASK);
+
+	pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
+						       sizeof(pmd)));
+	if (!pmd_present(pmd))
+		return 0;
+	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	if (pmd_large(pmd))
+		return pa + (vaddr & ~PMD_MASK);
+
+	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
+						       sizeof(pte)));
+	if (!pte_present(pte))
+		return 0;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+
+	return pa | (vaddr & ~PAGE_MASK);
+}
+
+/*
+ * Find a new area for the hypervisor supplied p2m list and relocate the p2m to
+ * this area.
+ */
+void __init xen_relocate_p2m(void)
+{
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys;
+	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
+	int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d;
+	pte_t *pt;
+	pmd_t *pmd;
+	pud_t *pud;
+	p4d_t *p4d = NULL;
+	pgd_t *pgd;
+	unsigned long *new_p2m;
+	int save_pud;
+
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
+	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
+	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
+	n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT;
+	if (PTRS_PER_P4D > 1)
+		n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	else
+		n_p4d = 0;
+	n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d;
+
+	new_area = xen_find_free_area(PFN_PHYS(n_frames));
+	if (!new_area) {
+		xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
+		BUG();
+	}
+
+	/*
+	 * Setup the page tables for addressing the new p2m list.
+	 * We have asked the hypervisor to map the p2m list at the user address
+	 * PUD_SIZE. It may have done so, or it may have used a kernel space
+	 * address depending on the Xen version.
+	 * To avoid any possible virtual address collision, just use
+	 * 2 * PUD_SIZE for the new area.
+	 */
+	p4d_phys = new_area;
+	pud_phys = p4d_phys + PFN_PHYS(n_p4d);
+	pmd_phys = pud_phys + PFN_PHYS(n_pud);
+	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
+	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
+
+	pgd = __va(read_cr3());
+	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
+	idx_p4d = 0;
+	save_pud = n_pud;
+	do {
+		if (n_p4d > 0) {
+			p4d = early_memremap(p4d_phys, PAGE_SIZE);
+			clear_page(p4d);
+			n_pud = min(save_pud, PTRS_PER_P4D);
+		}
+		for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+			pud = early_memremap(pud_phys, PAGE_SIZE);
+			clear_page(pud);
+			for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+				 idx_pmd++) {
+				pmd = early_memremap(pmd_phys, PAGE_SIZE);
+				clear_page(pmd);
+				for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+					 idx_pt++) {
+					pt = early_memremap(pt_phys, PAGE_SIZE);
+					clear_page(pt);
+					for (idx_pte = 0;
+						 idx_pte < min(n_pte, PTRS_PER_PTE);
+						 idx_pte++) {
+						set_pte(pt + idx_pte,
+								pfn_pte(p2m_pfn, PAGE_KERNEL));
+						p2m_pfn++;
+					}
+					n_pte -= PTRS_PER_PTE;
+					early_memunmap(pt, PAGE_SIZE);
+					make_lowmem_page_readonly(__va(pt_phys));
+					pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+							PFN_DOWN(pt_phys));
+					set_pmd(pmd + idx_pt,
+							__pmd(_PAGE_TABLE | pt_phys));
+					pt_phys += PAGE_SIZE;
+				}
+				n_pt -= PTRS_PER_PMD;
+				early_memunmap(pmd, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pmd_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+						PFN_DOWN(pmd_phys));
+				set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+				pmd_phys += PAGE_SIZE;
+			}
+			n_pmd -= PTRS_PER_PUD;
+			early_memunmap(pud, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pud_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+			if (n_p4d > 0)
+				set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys));
+			else
+				set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+			pud_phys += PAGE_SIZE;
+		}
+		if (n_p4d > 0) {
+			save_pud -= PTRS_PER_P4D;
+			early_memunmap(p4d, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(p4d_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys));
+			set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys));
+			p4d_phys += PAGE_SIZE;
+		}
+	} while (++idx_p4d < n_p4d);
+
+	/* Now copy the old p2m info to the new area. */
+	memcpy(new_p2m, xen_p2m_addr, size);
+	xen_p2m_addr = new_p2m;
+
+	/* Release the old p2m list and set new list info. */
+	p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
+	BUG_ON(!p2m_pfn);
+	p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
+
+	if (xen_start_info->mfn_list < __START_KERNEL_map) {
+		pfn = xen_start_info->first_p2m_pfn;
+		pfn_end = xen_start_info->first_p2m_pfn +
+			  xen_start_info->nr_p2m_frames;
+		set_pgd(pgd + 1, __pgd(0));
+	} else {
+		pfn = p2m_pfn;
+		pfn_end = p2m_pfn_end;
+	}
+
+	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
+	while (pfn < pfn_end) {
+		if (pfn == p2m_pfn) {
+			pfn = p2m_pfn_end;
+			continue;
+		}
+		make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+		pfn++;
+	}
+
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+	xen_start_info->first_p2m_pfn =  PFN_DOWN(new_area);
+	xen_start_info->nr_p2m_frames = n_frames;
+}
+
+#else	/* !CONFIG_X86_64 */
+static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
+
+static void __init xen_write_cr3_init(unsigned long cr3)
+{
+	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
+
+	BUG_ON(read_cr3() != __pa(initial_page_table));
+	BUG_ON(cr3 != __pa(swapper_pg_dir));
+
+	/*
+	 * We are switching to swapper_pg_dir for the first time (from
+	 * initial_page_table) and therefore need to mark that page
+	 * read-only and then pin it.
+	 *
+	 * Xen disallows sharing of kernel PMDs for PAE
+	 * guests. Therefore we must copy the kernel PMD from
+	 * initial_page_table into a new kernel PMD to be used in
+	 * swapper_pg_dir.
+	 */
+	swapper_kernel_pmd =
+		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
+	copy_page(swapper_kernel_pmd, initial_kernel_pmd);
+	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
+	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
+
+	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+	xen_write_cr3(cr3);
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
+
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	set_page_prot(initial_page_table, PAGE_KERNEL);
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
+
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
+}
+
+/*
+ * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
+ * not the first page table in the page table pool.
+ * Iterate through the initial page tables to find the real page table base.
+ */
+static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+{
+	phys_addr_t pt_base, paddr;
+	unsigned pmdidx;
+
+	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
+
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
+		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
+			paddr = m2p(pmd[pmdidx].pmd);
+			pt_base = min(pt_base, paddr);
+		}
+
+	return pt_base;
+}
+
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+	pmd_t *kernel_pmd;
+
+	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+
+	xen_pt_base = xen_find_pt_base(kernel_pmd);
+	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
+
+	initial_kernel_pmd =
+		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
+
+	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
+
+	copy_page(initial_kernel_pmd, kernel_pmd);
+
+	xen_map_identity_early(initial_kernel_pmd, max_pfn);
+
+	copy_page(initial_page_table, pgd);
+	initial_page_table[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
+
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
+	set_page_prot(initial_page_table, PAGE_KERNEL_RO);
+	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
+
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	xen_write_cr3(__pa(initial_page_table));
+
+	memblock_reserve(xen_pt_base, xen_pt_size);
+}
+#endif	/* CONFIG_X86_64 */
+
+void __init xen_reserve_special_pages(void)
+{
+	phys_addr_t paddr;
+
+	memblock_reserve(__pa(xen_start_info), PAGE_SIZE);
+	if (xen_start_info->store_mfn) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+	if (!xen_initial_domain()) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+}
+
+void __init xen_pt_check_e820(void)
+{
+	if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
+		xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
+		BUG();
+	}
+}
+
+static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+
+static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
+{
+	pte_t pte;
+
+	phys >>= PAGE_SHIFT;
+
+	switch (idx) {
+	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
+	case FIX_RO_IDT:
+#ifdef CONFIG_X86_32
+	case FIX_WP_TEST:
+# ifdef CONFIG_HIGHMEM
+	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
+# endif
+#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
+	case VSYSCALL_PAGE:
+#endif
+	case FIX_TEXT_POKE0:
+	case FIX_TEXT_POKE1:
+	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
+		/* All local page mappings */
+		pte = pfn_pte(phys, prot);
+		break;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	case FIX_APIC_BASE:	/* maps dummy local APIC */
+		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+		break;
+#endif
+
+#ifdef CONFIG_X86_IO_APIC
+	case FIX_IO_APIC_BASE_0 ... FIX_IO_APIC_BASE_END:
+		/*
+		 * We just don't map the IO APIC - all access is via
+		 * hypercalls.  Keep the address in the pte for reference.
+		 */
+		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+		break;
+#endif
+
+	case FIX_PARAVIRT_BOOTMAP:
+		/* This is an MFN, but it isn't an IO mapping from the
+		   IO domain */
+		pte = mfn_pte(phys, prot);
+		break;
+
+	default:
+		/* By default, set_fixmap is used for hardware mappings */
+		pte = mfn_pte(phys, prot);
+		break;
+	}
+
+	__native_set_fixmap(idx, pte);
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+	/* Replicate changes to map the vsyscall page into the user
+	   pagetable vsyscall mapping. */
+	if (idx == VSYSCALL_PAGE) {
+		unsigned long vaddr = __fix_to_virt(idx);
+		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
+	}
+#endif
+}
+
+static void __init xen_post_allocator_init(void)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	pv_mmu_ops.set_pte = xen_set_pte;
+	pv_mmu_ops.set_pmd = xen_set_pmd;
+	pv_mmu_ops.set_pud = xen_set_pud;
+#if CONFIG_PGTABLE_LEVELS >= 4
+	pv_mmu_ops.set_p4d = xen_set_p4d;
+#endif
+
+	/* This will work as long as patching hasn't happened yet
+	   (which it hasn't) */
+	pv_mmu_ops.alloc_pte = xen_alloc_pte;
+	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
+	pv_mmu_ops.release_pte = xen_release_pte;
+	pv_mmu_ops.release_pmd = xen_release_pmd;
+#if CONFIG_PGTABLE_LEVELS >= 4
+	pv_mmu_ops.alloc_pud = xen_alloc_pud;
+	pv_mmu_ops.release_pud = xen_release_pud;
+#endif
+	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
+
+#ifdef CONFIG_X86_64
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
+	SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
+	xen_mark_init_mm_pinned();
+}
+
+static void xen_leave_lazy_mmu(void)
+{
+	preempt_disable();
+	xen_mc_flush();
+	paravirt_leave_lazy_mmu();
+	preempt_enable();
+}
+
+static const struct pv_mmu_ops xen_mmu_ops __initconst = {
+	.read_cr2 = xen_read_cr2,
+	.write_cr2 = xen_write_cr2,
+
+	.read_cr3 = xen_read_cr3,
+	.write_cr3 = xen_write_cr3_init,
+
+	.flush_tlb_user = xen_flush_tlb,
+	.flush_tlb_kernel = xen_flush_tlb,
+	.flush_tlb_single = xen_flush_tlb_single,
+	.flush_tlb_others = xen_flush_tlb_others,
+
+	.pte_update = paravirt_nop,
+
+	.pgd_alloc = xen_pgd_alloc,
+	.pgd_free = xen_pgd_free,
+
+	.alloc_pte = xen_alloc_pte_init,
+	.release_pte = xen_release_pte_init,
+	.alloc_pmd = xen_alloc_pmd_init,
+	.release_pmd = xen_release_pmd_init,
+
+	.set_pte = xen_set_pte_init,
+	.set_pte_at = xen_set_pte_at,
+	.set_pmd = xen_set_pmd_hyper,
+
+	.ptep_modify_prot_start = __ptep_modify_prot_start,
+	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
+
+	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
+	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
+
+	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
+	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
+
+#ifdef CONFIG_X86_PAE
+	.set_pte_atomic = xen_set_pte_atomic,
+	.pte_clear = xen_pte_clear,
+	.pmd_clear = xen_pmd_clear,
+#endif	/* CONFIG_X86_PAE */
+	.set_pud = xen_set_pud_hyper,
+
+	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
+	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
+
+#if CONFIG_PGTABLE_LEVELS >= 4
+	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
+	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
+	.set_p4d = xen_set_p4d_hyper,
+
+	.alloc_pud = xen_alloc_pmd_init,
+	.release_pud = xen_release_pmd_init,
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+
+	.activate_mm = xen_activate_mm,
+	.dup_mmap = xen_dup_mmap,
+	.exit_mmap = xen_exit_mmap,
+
+	.lazy_mode = {
+		.enter = paravirt_enter_lazy_mmu,
+		.leave = xen_leave_lazy_mmu,
+		.flush = paravirt_flush_lazy_mmu,
+	},
+
+	.set_fixmap = xen_set_fixmap,
+};
+
+void __init xen_init_mmu_ops(void)
+{
+	x86_init.paging.pagetable_init = xen_pagetable_init;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	pv_mmu_ops = xen_mmu_ops;
+
+	memset(dummy_mapping, 0xff, PAGE_SIZE);
+}
+
+/* Protected by xen_reservation_lock. */
+#define MAX_CONTIG_ORDER 9 /* 2MB */
+static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
+
+#define VOID_PTE (mfn_pte(0, __pgprot(0)))
+static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
+				unsigned long *in_frames,
+				unsigned long *out_frames)
+{
+	int i;
+	struct multicall_space mcs;
+
+	xen_mc_batch();
+	for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) {
+		mcs = __xen_mc_entry(0);
+
+		if (in_frames)
+			in_frames[i] = virt_to_mfn(vaddr);
+
+		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
+		__set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+
+		if (out_frames)
+			out_frames[i] = virt_to_pfn(vaddr);
+	}
+	xen_mc_issue(0);
+}
+
+/*
+ * Update the pfn-to-mfn mappings for a virtual address range, either to
+ * point to an array of mfns, or contiguously from a single starting
+ * mfn.
+ */
+static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
+				     unsigned long *mfns,
+				     unsigned long first_mfn)
+{
+	unsigned i, limit;
+	unsigned long mfn;
+
+	xen_mc_batch();
+
+	limit = 1u << order;
+	for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) {
+		struct multicall_space mcs;
+		unsigned flags;
+
+		mcs = __xen_mc_entry(0);
+		if (mfns)
+			mfn = mfns[i];
+		else
+			mfn = first_mfn + i;
+
+		if (i < (limit - 1))
+			flags = 0;
+		else {
+			if (order == 0)
+				flags = UVMF_INVLPG | UVMF_ALL;
+			else
+				flags = UVMF_TLB_FLUSH | UVMF_ALL;
+		}
+
+		MULTI_update_va_mapping(mcs.mc, vaddr,
+				mfn_pte(mfn, PAGE_KERNEL), flags);
+
+		set_phys_to_machine(virt_to_pfn(vaddr), mfn);
+	}
+
+	xen_mc_issue(0);
+}
+
+/*
+ * Perform the hypercall to exchange a region of our pfns to point to
+ * memory with the required contiguous alignment.  Takes the pfns as
+ * input, and populates mfns as output.
+ *
+ * Returns a success code indicating whether the hypervisor was able to
+ * satisfy the request or not.
+ */
+static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
+			       unsigned long *pfns_in,
+			       unsigned long extents_out,
+			       unsigned int order_out,
+			       unsigned long *mfns_out,
+			       unsigned int address_bits)
+{
+	long rc;
+	int success;
+
+	struct xen_memory_exchange exchange = {
+		.in = {
+			.nr_extents   = extents_in,
+			.extent_order = order_in,
+			.extent_start = pfns_in,
+			.domid        = DOMID_SELF
+		},
+		.out = {
+			.nr_extents   = extents_out,
+			.extent_order = order_out,
+			.extent_start = mfns_out,
+			.address_bits = address_bits,
+			.domid        = DOMID_SELF
+		}
+	};
+
+	BUG_ON(extents_in << order_in != extents_out << order_out);
+
+	rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange);
+	success = (exchange.nr_exchanged == extents_in);
+
+	BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0)));
+	BUG_ON(success && (rc != 0));
+
+	return success;
+}
+
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
+{
+	unsigned long *in_frames = discontig_frames, out_frame;
+	unsigned long  flags;
+	int            success;
+	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
+
+	/*
+	 * Currently an auto-translated guest will not perform I/O, nor will
+	 * it require PAE page directories below 4GB. Therefore any calls to
+	 * this function are redundant and can be ignored.
+	 */
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
+	if (unlikely(order > MAX_CONTIG_ORDER))
+		return -ENOMEM;
+
+	memset((void *) vstart, 0, PAGE_SIZE << order);
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	/* 1. Zap current PTEs, remembering MFNs. */
+	xen_zap_pfn_range(vstart, order, in_frames, NULL);
+
+	/* 2. Get a new contiguous memory extent. */
+	out_frame = virt_to_pfn(vstart);
+	success = xen_exchange_memory(1UL << order, 0, in_frames,
+				      1, order, &out_frame,
+				      address_bits);
+
+	/* 3. Map the new extent in place of old pages. */
+	if (success)
+		xen_remap_exchanged_ptes(vstart, order, NULL, out_frame);
+	else
+		xen_remap_exchanged_ptes(vstart, order, in_frames, 0);
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+
+	*dma_handle = virt_to_machine(vstart).maddr;
+	return success ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
+{
+	unsigned long *out_frames = discontig_frames, in_frame;
+	unsigned long  flags;
+	int success;
+	unsigned long vstart;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	if (unlikely(order > MAX_CONTIG_ORDER))
+		return;
+
+	vstart = (unsigned long)phys_to_virt(pstart);
+	memset((void *) vstart, 0, PAGE_SIZE << order);
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	/* 1. Find start MFN of contiguous extent. */
+	in_frame = virt_to_mfn(vstart);
+
+	/* 2. Zap current PTEs. */
+	xen_zap_pfn_range(vstart, order, NULL, out_frames);
+
+	/* 3. Do the exchange for non-contiguous MFNs. */
+	success = xen_exchange_memory(1, order, &in_frame, 1UL << order,
+					0, out_frames, 0);
+
+	/* 4. Map new pages in place of old pages. */
+	if (success)
+		xen_remap_exchanged_ptes(vstart, order, out_frames, 0);
+	else
+		xen_remap_exchanged_ptes(vstart, order, NULL, in_frame);
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+}
+EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
+
+#ifdef CONFIG_KEXEC_CORE
+phys_addr_t paddr_vmcoreinfo_note(void)
+{
+	if (xen_pv_domain())
+		return virt_to_machine(&vmcoreinfo_note).maddr;
+	else
+		return __pa_symbol(&vmcoreinfo_note);
+}
+#endif /* CONFIG_KEXEC_CORE */

arch/x86/xen/pmu.h

···
 #include <xen/interface/xenpmu.h>
 
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
+#ifdef CONFIG_XEN_HAVE_VPMU
 void xen_pmu_init(int cpu);
 void xen_pmu_finish(int cpu);
+#else
+static inline void xen_pmu_init(int cpu) {}
+static inline void xen_pmu_finish(int cpu) {}
+#endif
 bool is_xen_pmu(int cpu);
 bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
 bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);

arch/x86/xen/smp.c

···
-/*
- * Xen SMP support
- *
- * This file implements the Xen versions of smp_ops.  SMP under Xen is
- * very straightforward.  Bringing a CPU up is simply a matter of
- * loading its initial context and setting it running.
- *
- * IPIs are handled through the Xen event mechanism.
- *
- * Because virtual CPUs can be scheduled onto any real CPU, there's no
- * useful topology information for the kernel to make use of.  As a
- * result, all CPUs are treated as if they're single-core and
- * single-threaded.
- */
-#include <linux/sched.h>
-#include <linux/err.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
-#include <linux/irq_work.h>
-#include <linux/tick.h>
-#include <linux/nmi.h>
+#include <linux/slab.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
 
-#include <asm/paravirt.h>
-#include <asm/desc.h>
-#include <asm/pgtable.h>
-#include <asm/cpu.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/vcpu.h>
-#include <xen/interface/xenpmu.h>
-
-#include <asm/xen/interface.h>
-#include <asm/xen/hypercall.h>
-
-#include <xen/xen.h>
-#include <xen/page.h>
 #include <xen/events.h>
 
 #include <xen/hvc-console.h>
 #include "xen-ops.h"
-#include "mmu.h"
 #include "smp.h"
-#include "pmu.h"
 
-cpumask_var_t xen_cpu_initialized_map;
-
-struct xen_common_irq {
-	int irq;
-	char *name;
-};
 static DEFINE_PER_CPU(struct xen_common_irq, xen_resched_irq) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 };
-static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .irq = -1 };
-static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
-static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
 
 /*
  * Reschedule call back.
···
 	scheduler_ipi();
 
 	return IRQ_HANDLED;
-}
-
-static void cpu_bringup(void)
-{
-	int cpu;
-
-	cpu_init();
-	touch_softlockup_watchdog();
-	preempt_disable();
-
-	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
-	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
-		xen_enable_sysenter();
-		xen_enable_syscall();
-	}
-	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
-	cpu_data(cpu).x86_max_cores = 1;
-	set_cpu_sibling_map(cpu);
-
-	xen_setup_cpu_clockevents();
-
-	notify_cpu_starting(cpu);
-
-	set_cpu_online(cpu, true);
-
-	cpu_set_state_online(cpu);  /* Implies full memory barrier. */
-
-	/* We can take interrupts now: we're officially "up". */
-	local_irq_enable();
-}
-
-asmlinkage __visible void cpu_bringup_and_idle(void)
-{
-	cpu_bringup();
-	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 void xen_smp_intr_free(unsigned int cpu)
···
 		kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
 		per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
 	}
-	if (xen_hvm_domain())
-		return;
+}
 
-	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
-		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
-		per_cpu(xen_irq_work, cpu).irq = -1;
-		kfree(per_cpu(xen_irq_work, cpu).name);
-		per_cpu(xen_irq_work, cpu).name = NULL;
-	}
-
-	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
-		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
-		per_cpu(xen_pmu_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_pmu_irq, cpu).name);
-		per_cpu(xen_pmu_irq, cpu).name = NULL;
-	}
-};
 int xen_smp_intr_init(unsigned int cpu)
 {
 	int rc;
-	char *resched_name, *callfunc_name, *debug_name, *pmu_name;
+	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
···
 	per_cpu(xen_callfuncsingle_irq, cpu).irq = rc;
 	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 
-	/*
-	 * The IRQ worker on PVHVM goes through the native path and uses the
-	 * IPI mechanism.
-	 */
-	if (xen_hvm_domain())
-		return 0;
-
-	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
-	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
-				    cpu,
-				    xen_irq_work_interrupt,
-				    IRQF_PERCPU|IRQF_NOBALANCING,
-				    callfunc_name,
-				    NULL);
-	if (rc < 0)
-		goto fail;
-	per_cpu(xen_irq_work, cpu).irq = rc;
-	per_cpu(xen_irq_work, cpu).name = callfunc_name;
-
-	if (is_xen_pmu(cpu)) {
-		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
-		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
-					     xen_pmu_irq_handler,
-					     IRQF_PERCPU|IRQF_NOBALANCING,
-					     pmu_name, NULL);
-		if (rc < 0)
-			goto fail;
-		per_cpu(xen_pmu_irq, cpu).irq = rc;
-		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
-	}
-
 	return 0;
 
  fail:
···
 	return rc;
 }
 
-static void __init xen_fill_possible_map(void)
-{
-	int i, rc;
-
-	if (xen_initial_domain())
-		return;
-
-	for (i = 0; i < nr_cpu_ids; i++) {
-		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
-		if (rc >= 0) {
-			num_processors++;
-			set_cpu_possible(i, true);
-		}
-	}
-}
-
-static void __init xen_filter_cpu_maps(void)
-{
-	int i, rc;
-	unsigned int subtract = 0;
-
-	if (!xen_initial_domain())
-		return;
-
-	num_processors = 0;
-	disabled_cpus = 0;
-	for (i = 0; i < nr_cpu_ids; i++) {
-		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
-		if (rc >= 0) {
-			num_processors++;
-			set_cpu_possible(i, true);
-		} else {
-			set_cpu_possible(i, false);
-			set_cpu_present(i, false);
-			subtract++;
-		}
-	}
-#ifdef CONFIG_HOTPLUG_CPU
-	/* This is akin to using 'nr_cpus' on the Linux command line.
-	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
-	 * have up to X, while nr_cpu_ids is greater than X. This
-	 * normally is not a problem, except when CPU hotplugging
-	 * is involved and then there might be more than X CPUs
-	 * in the guest - which will not work as there is no
-	 * hypercall to expand the max number of VCPUs an already
-	 * running guest has. So cap it up to X. */
-	if (subtract)
-		nr_cpu_ids = nr_cpu_ids - subtract;
-#endif
-
-}
-
-static void __init xen_smp_prepare_boot_cpu(void)
-{
-	BUG_ON(smp_processor_id() != 0);
-	native_smp_prepare_boot_cpu();
-
-	if (xen_pv_domain()) {
-		if (!xen_feature(XENFEAT_writable_page_tables))
-			/* We've switched to the "real" per-cpu gdt, so make
-			 * sure the old memory can be recycled. */
-			make_lowmem_page_readwrite(xen_initial_gdt);
-
-#ifdef CONFIG_X86_32
-		/*
-		 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
-		 * expects __USER_DS
-		 */
-		loadsegment(ds, __USER_DS);
-		loadsegment(es, __USER_DS);
-#endif
-
-		xen_filter_cpu_maps();
-		xen_setup_vcpu_info_placement();
-	}
-
-	/*
-	 * Setup vcpu_info for boot CPU.
-	 */
-	if (xen_hvm_domain())
-		xen_vcpu_setup(0);
-
-	/*
-	 * The alternative logic (which patches the unlock/lock) runs before
-	 * the smp bootup up code is activated. Hence we need to set this up
-	 * the core kernel is being patched. Otherwise we will have only
-	 * modules patched but not core code.
-	 */
-	xen_init_spinlocks();
-}
-
-static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
-{
-	unsigned cpu;
-	unsigned int i;
-
-	if (skip_ioapic_setup) {
-		char *m = (max_cpus == 0) ?
-			"The nosmp parameter is incompatible with Xen; " \
-			"use Xen dom0_max_vcpus=1 parameter" :
-			"The noapic parameter is incompatible with Xen";
-
-		xen_raw_printk(m);
-		panic(m);
-	}
-	xen_init_lock_cpu(0);
-
-	smp_store_boot_cpu_info();
-	cpu_data(0).x86_max_cores = 1;
-
-	for_each_possible_cpu(i) {
-		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
-	}
-	set_cpu_sibling_map(0);
-
-	xen_pmu_init(0);
-
-	if (xen_smp_intr_init(0))
-		BUG();
-
-	if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
-		panic("could not allocate xen_cpu_initialized_map\n");
-
-	cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
-
-	/* Restrict the possible_map according to max_cpus. */
-	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
-		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
-			continue;
-		set_cpu_possible(cpu, false);
-	}
-
-	for_each_possible_cpu(cpu)
-		set_cpu_present(cpu, true);
-}
-
-static int
-cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
-{
-	struct vcpu_guest_context *ctxt;
-	struct desc_struct *gdt;
-	unsigned long gdt_mfn;
-
-	/* used to tell cpu_init() that it can proceed with initialization */
-	cpumask_set_cpu(cpu, cpu_callout_mask);
-	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
-		return 0;
-
-	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
-	if (ctxt == NULL)
-		return -ENOMEM;
-
-	gdt = get_cpu_gdt_rw(cpu);
-
-#ifdef CONFIG_X86_32
-	ctxt->user_regs.fs = __KERNEL_PERCPU;
-	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
-#endif
-	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
-
-	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-	ctxt->flags = VGCF_IN_KERNEL;
-	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
-	ctxt->user_regs.ds = __USER_DS;
-	ctxt->user_regs.es = __USER_DS;
-	ctxt->user_regs.ss = __KERNEL_DS;
-
-	xen_copy_trap_info(ctxt->trap_ctxt);
-
-	ctxt->ldt_ents = 0;
-
-	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
-
-	gdt_mfn = arbitrary_virt_to_mfn(gdt);
-	make_lowmem_page_readonly(gdt);
-	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
-
-	ctxt->gdt_frames[0] = gdt_mfn;
-	ctxt->gdt_ents      = GDT_ENTRIES;
-
-	ctxt->kernel_ss = __KERNEL_DS;
-	ctxt->kernel_sp = idle->thread.sp0;
-
-#ifdef CONFIG_X86_32
-	ctxt->event_callback_cs     = __KERNEL_CS;
-	ctxt->failsafe_callback_cs  = __KERNEL_CS;
-#else
-	ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
-	ctxt->event_callback_eip    =
-		(unsigned long)xen_hypervisor_callback;
-	ctxt->failsafe_callback_eip =
-		(unsigned long)xen_failsafe_callback;
-	ctxt->user_regs.cs = __KERNEL_CS;
-	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-
-	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
-	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
-	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
-		BUG();
-
-	kfree(ctxt);
-	return 0;
-}
-
-static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
-{
-	int rc;
-
-	common_cpu_up(cpu, idle);
-
-	xen_setup_runstate_info(cpu);
-
-	/*
-	 * PV VCPUs are always successfully taken down (see 'while' loop
-	 * in xen_cpu_die()), so -EBUSY is an error.
-	 */
-	rc = cpu_check_up_prepare(cpu);
-	if (rc)
-		return rc;
-
-	/* make sure interrupts start blocked */
-	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
-
-	rc = cpu_initialize_context(cpu, idle);
-	if (rc)
-		return rc;
-
-	xen_pmu_init(cpu);
-
-	rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
-	BUG_ON(rc);
-
-	while (cpu_report_state(cpu) != CPU_ONLINE)
-		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
-
-	return 0;
-}
-
-static void xen_smp_cpus_done(unsigned int max_cpus)
-{
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-static int xen_cpu_disable(void)
-{
-	unsigned int cpu = smp_processor_id();
-	if (cpu == 0)
-		return -EBUSY;
-
-	cpu_disable_common();
-
-	load_cr3(swapper_pg_dir);
-	return 0;
-}
-
-static void xen_cpu_die(unsigned int cpu)
-{
-	while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up,
-						     xen_vcpu_nr(cpu), NULL)) {
-		__set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule_timeout(HZ/10);
-	}
-
-	if (common_cpu_die(cpu) == 0) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-		xen_teardown_timer(cpu);
-		xen_pmu_finish(cpu);
-	}
-}
-
-static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
-{
-	play_dead_common();
-	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
-	cpu_bringup();
-	/*
-	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
-	 * clears certain data that the cpu_idle loop (which called us
-	 * and that we return from) expects. The only way to get that
-	 * data back is to call:
-	 */
-	tick_nohz_idle_enter();
-
-	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
-}
-
-#else /* !CONFIG_HOTPLUG_CPU */
-static int xen_cpu_disable(void)
-{
-	return -ENOSYS;
-}
-
-static void xen_cpu_die(unsigned int cpu)
-{
-	BUG();
-}
-
-static void xen_play_dead(void)
-{
-	BUG();
-}
-
-#endif
-static void stop_self(void *v)
-{
-	int cpu = smp_processor_id();
-
-	/* make sure we're not pinning something down */
-	load_cr3(swapper_pg_dir);
-	/* should set up a minimal gdt */
-
-	set_cpu_online(cpu, false);
-
-	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL);
-	BUG();
-}
-
-static void xen_stop_other_cpus(int wait)
-{
-	smp_call_function(stop_self, NULL, wait);
-}
-
-static void xen_smp_send_reschedule(int cpu)
+void xen_smp_send_reschedule(int cpu)
 {
 	xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
 }
···
 		xen_send_IPI_one(cpu, vector);
 }
 
-static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
+void xen_smp_send_call_function_ipi(const struct cpumask *mask)
 {
 	int cpu;
 
···
 	}
 }
 
-static void xen_smp_send_call_function_single_ipi(int cpu)
+void xen_smp_send_call_function_single_ipi(int cpu)
 {
 	__xen_send_IPI_mask(cpumask_of(cpu),
 			  XEN_CALL_FUNCTION_SINGLE_VECTOR);
···
 	irq_exit();
 
 	return IRQ_HANDLED;
-}
-
-static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
-{
-	irq_enter();
-	irq_work_run();
-	inc_irq_stat(apic_irq_work_irqs);
-	irq_exit();
-
-	return IRQ_HANDLED;
-}
-
-static const struct smp_ops xen_smp_ops __initconst = {
-	.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
-	.smp_prepare_cpus = xen_smp_prepare_cpus,
-	.smp_cpus_done = xen_smp_cpus_done,
-
-	.cpu_up = xen_cpu_up,
-	.cpu_die = xen_cpu_die,
-	.cpu_disable = xen_cpu_disable,
-	.play_dead = xen_play_dead,
-
-	.stop_other_cpus = xen_stop_other_cpus,
-	.smp_send_reschedule = xen_smp_send_reschedule,
-
-	.send_call_func_ipi = xen_smp_send_call_function_ipi,
-	.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
-};
-
-void __init xen_smp_init(void)
-{
-	smp_ops = xen_smp_ops;
-	xen_fill_possible_map();
-}
-
-static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
-{
-	native_smp_prepare_cpus(max_cpus);
-	WARN_ON(xen_smp_intr_init(0));
-
-	xen_init_lock_cpu(0);
-}
-
-void __init xen_hvm_smp_init(void)
-{
-	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
-	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
-	smp_ops.cpu_die = xen_cpu_die;
-	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
-	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
-	smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
 }

arch/x86/xen/smp.h

···
 
 extern int xen_smp_intr_init(unsigned int cpu);
 extern void xen_smp_intr_free(unsigned int cpu);
+int xen_smp_intr_init_pv(unsigned int cpu);
+void xen_smp_intr_free_pv(unsigned int cpu);
 
+void xen_smp_send_reschedule(int cpu);
+void xen_smp_send_call_function_ipi(const struct cpumask *mask);
+void xen_smp_send_call_function_single_ipi(int cpu);
+
+struct xen_common_irq {
+	int irq;
+	char *name;
+};
 #else /* CONFIG_SMP */
 
 static inline int xen_smp_intr_init(unsigned int cpu)
···
 	return 0;
 }
 static inline void xen_smp_intr_free(unsigned int cpu) {}
+
+static inline int xen_smp_intr_init_pv(unsigned int cpu)
+{
+	return 0;
+}
+static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
 #endif /* CONFIG_SMP */
 
 #endif

arch/x86/xen/smp_hvm.c

···
+#include <asm/smp.h>
+
+#include <xen/events.h>
+
+#include "xen-ops.h"
+#include "smp.h"
+
+
+static void __init xen_hvm_smp_prepare_boot_cpu(void)
+{
+	BUG_ON(smp_processor_id() != 0);
+	native_smp_prepare_boot_cpu();
+
+	/*
+	 * Setup vcpu_info for boot CPU.
+	 */
+	xen_vcpu_setup(0);
+
+	/*
+	 * The alternative logic (which patches the unlock/lock) runs before
+	 * the smp bootup up code is activated. Hence we need to set this up
+	 * the core kernel is being patched. Otherwise we will have only
+	 * modules patched but not core code.
+	 */
+	xen_init_spinlocks();
+}
+
+static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+	native_smp_prepare_cpus(max_cpus);
+	WARN_ON(xen_smp_intr_init(0));
+
+	xen_init_lock_cpu(0);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void xen_hvm_cpu_die(unsigned int cpu)
+{
+	if (common_cpu_die(cpu) == 0) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+		xen_teardown_timer(cpu);
+	}
+}
+#else
+static void xen_hvm_cpu_die(unsigned int cpu)
+{
+	BUG();
+}
+#endif
+
+void __init xen_hvm_smp_init(void)
+{
+	if (!xen_have_vector_callback)
+		return;
+
+	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+	smp_ops.cpu_die = xen_hvm_cpu_die;
+	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
+	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
+}

arch/x86/xen/smp_pv.c

···
+/*
+ * Xen SMP support
+ *
+ * This file implements the Xen versions of smp_ops.  SMP under Xen is
+ * very straightforward.  Bringing a CPU up is simply a matter of
+ * loading its initial context and setting it running.
+ *
+ * IPIs are handled through the Xen event mechanism.
+ *
+ * Because virtual CPUs can be scheduled onto any real CPU, there's no
+ * useful topology information for the kernel to make use of.  As a
+ * result, all CPUs are treated as if they're single-core and
+ * single-threaded.
+ */
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/irq_work.h>
+#include <linux/tick.h>
+#include <linux/nmi.h>
+
+#include <asm/paravirt.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/cpu.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/vcpu.h>
+#include <xen/interface/xenpmu.h>
+
+#include <asm/xen/interface.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/page.h>
+#include <xen/events.h>
+
+#include <xen/hvc-console.h>
+#include "xen-ops.h"
+#include "mmu.h"
+#include "smp.h"
+#include "pmu.h"
+
+cpumask_var_t xen_cpu_initialized_map;
+
+static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
+static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
+
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
+
+static void cpu_bringup(void)
+{
+	int cpu;
+
+	cpu_init();
+	touch_softlockup_watchdog();
+	preempt_disable();
+
+	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
+	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
+		xen_enable_sysenter();
+		xen_enable_syscall();
+	}
+	cpu = smp_processor_id();
+	smp_store_cpu_info(cpu);
+	cpu_data(cpu).x86_max_cores = 1;
+	set_cpu_sibling_map(cpu);
+
+	xen_setup_cpu_clockevents();
+
+	notify_cpu_starting(cpu);
+
+	set_cpu_online(cpu, true);
+
+	cpu_set_state_online(cpu);  /* Implies full memory barrier. */
+
+	/* We can take interrupts now: we're officially "up". */
+	local_irq_enable();
+}
+
+asmlinkage __visible void cpu_bringup_and_idle(void)
+{
+	cpu_bringup();
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+void xen_smp_intr_free_pv(unsigned int cpu)
+{
+	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
+		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
+		per_cpu(xen_irq_work, cpu).irq = -1;
+		kfree(per_cpu(xen_irq_work, cpu).name);
+		per_cpu(xen_irq_work, cpu).name = NULL;
+	}
+
+	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
+		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
+		per_cpu(xen_pmu_irq, cpu).irq = -1;
+		kfree(per_cpu(xen_pmu_irq, cpu).name);
+		per_cpu(xen_pmu_irq, cpu).name = NULL;
+	}
+}
+
+int xen_smp_intr_init_pv(unsigned int cpu)
+{
+	int rc;
+	char *callfunc_name, *pmu_name;
+
+	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
+				    cpu,
+				    xen_irq_work_interrupt,
+				    IRQF_PERCPU|IRQF_NOBALANCING,
+				    callfunc_name,
+				    NULL);
+	if (rc < 0)
+		goto fail;
+	per_cpu(xen_irq_work, cpu).irq = rc;
+	per_cpu(xen_irq_work, cpu).name = callfunc_name;
+
+	if (is_xen_pmu(cpu)) {
+		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
+		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
+					     xen_pmu_irq_handler,
+					     IRQF_PERCPU|IRQF_NOBALANCING,
+					     pmu_name, NULL);
+		if (rc < 0)
+			goto fail;
+		per_cpu(xen_pmu_irq, cpu).irq = rc;
+		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
+	}
+
+	return 0;
+
+ fail:
+	xen_smp_intr_free_pv(cpu);
+	return rc;
+}
+
+static void __init xen_fill_possible_map(void)
+{
+	int i, rc;
+
+	if (xen_initial_domain())
+		return;
+
+	for (i = 0; i < nr_cpu_ids; i++) {
+		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
+		if (rc >= 0) {
+			num_processors++;
+			set_cpu_possible(i, true);
+		}
+	}
+}
+
+static void __init xen_filter_cpu_maps(void)
+{
+	int i, rc;
+	unsigned int subtract = 0;
+
+	if (!xen_initial_domain())
+		return;
+
+	num_processors = 0;
+	disabled_cpus = 0;
+	for (i = 0; i < nr_cpu_ids; i++) {
+		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
+		if (rc >= 0) {
+			num_processors++;
+			set_cpu_possible(i, true);
+		} else {
+			set_cpu_possible(i, false);
+			set_cpu_present(i, false);
+			subtract++;
+		}
+	}
+#ifdef CONFIG_HOTPLUG_CPU
+	/* This is akin to using 'nr_cpus' on the Linux command line.
+	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
+	 * have up to X, while nr_cpu_ids is greater than X. This
+	 * normally is not a problem, except when CPU hotplugging
+	 * is involved and then there might be more than X CPUs
+	 * in the guest - which will not work as there is no
+	 * hypercall to expand the max number of VCPUs an already
+	 * running guest has. So cap it up to X. */
+	if (subtract)
+		nr_cpu_ids = nr_cpu_ids - subtract;
+#endif
+
+}
+
+static void __init xen_pv_smp_prepare_boot_cpu(void)
+{
+	BUG_ON(smp_processor_id() != 0);
+	native_smp_prepare_boot_cpu();
+
+	if (!xen_feature(XENFEAT_writable_page_tables))
+		/* We've switched to the "real" per-cpu gdt, so make
+		 * sure the old memory can be recycled. */
+		make_lowmem_page_readwrite(xen_initial_gdt);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+	 * expects __USER_DS
+	 */
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+#endif
+
+	xen_filter_cpu_maps();
+	xen_setup_vcpu_info_placement();
+
+	/*
+	 * The alternative logic (which patches the unlock/lock) runs before
+	 * the smp bootup up code is activated. Hence we need to set this up
+	 * the core kernel is being patched. Otherwise we will have only
+	 * modules patched but not core code.
+	 */
+	xen_init_spinlocks();
+}
+
+static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
+{
+	unsigned cpu;
+	unsigned int i;
+
+	if (skip_ioapic_setup) {
+		char *m = (max_cpus == 0) ?
+			"The nosmp parameter is incompatible with Xen; " \
+			"use Xen dom0_max_vcpus=1 parameter" :
+			"The noapic parameter is incompatible with Xen";
+
+		xen_raw_printk(m);
+		panic(m);
+	}
+	xen_init_lock_cpu(0);
+
+	smp_store_boot_cpu_info();
+	cpu_data(0).x86_max_cores = 1;
+
+	for_each_possible_cpu(i) {
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+	}
+	set_cpu_sibling_map(0);
+
+	xen_pmu_init(0);
+
+	if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))
+		BUG();
+
+	if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
+		panic("could not allocate xen_cpu_initialized_map\n");
+
+	cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
+
+	/* Restrict the possible_map according to max_cpus. */
+	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
+		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
+			continue;
+		set_cpu_possible(cpu, false);
+	}
+
+	for_each_possible_cpu(cpu)
+		set_cpu_present(cpu, true);
+}
+
+static int
+cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
+{
+	struct vcpu_guest_context *ctxt;
+	struct desc_struct *gdt;
+	unsigned long gdt_mfn;
+
+	/* used to tell cpu_init() that it can proceed with initialization */
+	cpumask_set_cpu(cpu, cpu_callout_mask);
+	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
+		return 0;
+
+	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
+	if (ctxt == NULL)
+		return -ENOMEM;
+
+	gdt = get_cpu_gdt_rw(cpu);
+
+#ifdef CONFIG_X86_32
+	ctxt->user_regs.fs = __KERNEL_PERCPU;
+	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
+#endif
+	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
+
+	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
+	ctxt->flags = VGCF_IN_KERNEL;
+	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
+	ctxt->user_regs.ds = __USER_DS;
+	ctxt->user_regs.es = __USER_DS;
+	ctxt->user_regs.ss = __KERNEL_DS;
+
+	xen_copy_trap_info(ctxt->trap_ctxt);
+
+	ctxt->ldt_ents = 0;
+
+	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
+
+	gdt_mfn = arbitrary_virt_to_mfn(gdt);
+	make_lowmem_page_readonly(gdt);
+	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
+
+	ctxt->gdt_frames[0] = gdt_mfn;
+	ctxt->gdt_ents      = GDT_ENTRIES;
+
+	ctxt->kernel_ss = __KERNEL_DS;
+	ctxt->kernel_sp = idle->thread.sp0;
+
+#ifdef CONFIG_X86_32
+	ctxt->event_callback_cs     = __KERNEL_CS;
+	ctxt->failsafe_callback_cs  = __KERNEL_CS;
+#else
+	ctxt->gs_base_kernel = per_cpu_offset(cpu);
+#endif
+	ctxt->event_callback_eip    =
+		(unsigned long)xen_hypervisor_callback;
+	ctxt->failsafe_callback_eip =
+		(unsigned long)xen_failsafe_callback;
+	ctxt->user_regs.cs = __KERNEL_CS;
+	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
+
+	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
+	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
+	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
+		BUG();
+
+	kfree(ctxt);
+	return 0;
+}
+
+static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+	int rc;
+
+	common_cpu_up(cpu, idle);
+
+	xen_setup_runstate_info(cpu);
+
+	/*
+	 * PV VCPUs are always successfully taken down (see 'while' loop
+	 * in xen_cpu_die()), so -EBUSY is an error.
+	 */
+	rc = cpu_check_up_prepare(cpu);
+	if (rc)
+		return rc;
+
+	/* make sure interrupts start blocked */
+	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
+
+	rc = cpu_initialize_context(cpu, idle);
+	if (rc)
+		return rc;
+
+	xen_pmu_init(cpu);
+
+	rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
+	BUG_ON(rc);
+
+	while (cpu_report_state(cpu) != CPU_ONLINE)
+		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
+
+	return 0;
+}
+
+static void xen_pv_smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int xen_pv_cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+	if (cpu == 0)
+		return -EBUSY;
+
+	cpu_disable_common();
+
+	load_cr3(swapper_pg_dir);
+	return 0;
+}
+
+static void xen_pv_cpu_die(unsigned int cpu)
+{
+	while (HYPERVISOR_vcpu_op(VCPUOP_is_up,
+				  xen_vcpu_nr(cpu), NULL)) {
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(HZ/10);
+	}
+
+	if (common_cpu_die(cpu) == 0) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+		xen_teardown_timer(cpu);
+		xen_pmu_finish(cpu);
+	}
+}
+
+static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
+{
+	play_dead_common();
+	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
+	cpu_bringup();
+	/*
+	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
+	 * clears certain data that the cpu_idle loop (which called us
+	 * and that we return from) expects. The only way to get that
+	 * data back is to call:
+	 */
+	tick_nohz_idle_enter();
+
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+static int xen_pv_cpu_disable(void)
+{
+	return -ENOSYS;
+}
+
+static void xen_pv_cpu_die(unsigned int cpu)
+{
+	BUG();
+}
+
+static void xen_pv_play_dead(void)
+{
+	BUG();
+}
+
+#endif
+static void stop_self(void *v)
+{
+	int cpu = smp_processor_id();
+
+	/* make sure we're not pinning something down */
+	load_cr3(swapper_pg_dir);
+	/* should set up a minimal gdt */
+
+	set_cpu_online(cpu, false);
+
+	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL);
+	BUG();
+}
+
+static void xen_pv_stop_other_cpus(int wait)
+{
+	smp_call_function(stop_self, NULL, wait);
+}
+
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
+{
+	irq_enter();
+	irq_work_run();
+	inc_irq_stat(apic_irq_work_irqs);
+	irq_exit();
+
+	return IRQ_HANDLED;
+}
+
+static const struct smp_ops xen_smp_ops __initconst = {
+	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
+	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
+	.smp_cpus_done = xen_pv_smp_cpus_done,
+
+	.cpu_up = xen_pv_cpu_up,
+	.cpu_die = xen_pv_cpu_die,
+	.cpu_disable = xen_pv_cpu_disable,
+	.play_dead = xen_pv_play_dead,
+
+	.stop_other_cpus = xen_pv_stop_other_cpus,
+	.smp_send_reschedule = xen_smp_send_reschedule,
+
+	.send_call_func_ipi = xen_smp_send_call_function_ipi,
+	.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
+};
+
+void __init xen_smp_init(void)
+{
+	smp_ops = xen_smp_ops;
+	xen_fill_possible_map();
+}

arch/x86/xen/suspend.c

···
 #include "mmu.h"
 #include "pmu.h"
 
-static void xen_pv_pre_suspend(void)
-{
-	xen_mm_pin_all();
-
-	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
-	xen_start_info->console.domU.mfn =
-		mfn_to_pfn(xen_start_info->console.domU.mfn);
-
-	BUG_ON(!irqs_disabled());
-
-	HYPERVISOR_shared_info = &xen_dummy_shared_info;
-	if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP),
-					 __pte_ma(0), 0))
-		BUG();
-}
-
-static void xen_hvm_post_suspend(int suspend_cancelled)
-{
-#ifdef CONFIG_XEN_PVHVM
-	int cpu;
-	if (!suspend_cancelled)
-	    xen_hvm_init_shared_info();
-	xen_callback_vector();
-	xen_unplug_emulated_devices();
-	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		for_each_online_cpu(cpu) {
-			xen_setup_runstate_info(cpu);
-		}
-	}
-#endif
-}
-
-static void xen_pv_post_suspend(int suspend_cancelled)
-{
-	xen_build_mfn_list_list();
-
-	xen_setup_shared_info();
-
-	if (suspend_cancelled) {
-		xen_start_info->store_mfn =
-			pfn_to_mfn(xen_start_info->store_mfn);
-		xen_start_info->console.domU.mfn =
-			pfn_to_mfn(xen_start_info->console.domU.mfn);
-	} else {
-#ifdef CONFIG_SMP
-		BUG_ON(xen_cpu_initialized_map == NULL);
-		cpumask_copy(xen_cpu_initialized_map, cpu_online_mask);
-#endif
-		xen_vcpu_restore();
-	}
-
-	xen_mm_unpin_all();
-}
-
 void xen_arch_pre_suspend(void)
 {
 	if (xen_pv_domain())

arch/x86/xen/suspend_hvm.c

···
+#include <linux/types.h>
+
+#include <xen/xen.h>
+#include <xen/features.h>
+#include <xen/interface/features.h>
+
+#include "xen-ops.h"
+
+void xen_hvm_post_suspend(int suspend_cancelled)
+{
+	int cpu;
+
+	if (!suspend_cancelled)
+		xen_hvm_init_shared_info();
+	xen_callback_vector();
+	xen_unplug_emulated_devices();
+	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
+		for_each_online_cpu(cpu) {
+			xen_setup_runstate_info(cpu);
+		}
+	}
+}

arch/x86/xen/suspend_pv.c

···
+#include <linux/types.h>
+
+#include <asm/fixmap.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+#include "xen-ops.h"
+
+void xen_pv_pre_suspend(void)
+{
+	xen_mm_pin_all();
+
+	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
+	xen_start_info->console.domU.mfn =
+		mfn_to_pfn(xen_start_info->console.domU.mfn);
+
+	BUG_ON(!irqs_disabled());
+
+	HYPERVISOR_shared_info = &xen_dummy_shared_info;
+	if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP),
+					 __pte_ma(0), 0))
+		BUG();
+}
+
+void xen_pv_post_suspend(int suspend_cancelled)
+{
+	xen_build_mfn_list_list();
+
+	xen_setup_shared_info();
+
+	if (suspend_cancelled) {
+		xen_start_info->store_mfn =
+			pfn_to_mfn(xen_start_info->store_mfn);
+		xen_start_info->console.domU.mfn =
+			pfn_to_mfn(xen_start_info->console.domU.mfn);
+	} else {
+#ifdef CONFIG_SMP
+		BUG_ON(xen_cpu_initialized_map == NULL);
+		cpumask_copy(xen_cpu_initialized_map, cpu_online_mask);
+#endif
+		xen_vcpu_restore();
+	}
+
+	xen_mm_unpin_all();
+}

arch/x86/xen/time.c

···
 
 void __init xen_hvm_init_time_ops(void)
 {
+	/*
+	 * vector callback is needed otherwise we cannot receive interrupts
+	 * on cpu > 0 and at this point we don't know how many cpus are
+	 * available.
+	 */
+	if (!xen_have_vector_callback)
+		return;
+
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
 				"disable pv timer\n");

arch/x86/xen/xen-head.S

···
 #include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
+#ifdef CONFIG_XEN_PV
 	__INIT
 ENTRY(startup_xen)
 	cld
···
 	jmp xen_start_kernel
 
 	__FINIT
+#endif
 
 .pushsection .text
 	.balign PAGE_SIZE
···
 	/* Map the p2m table to a 512GB-aligned user address. */
 	ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M,       .quad PGDIR_SIZE)
 #endif
+#ifdef CONFIG_XEN_PV
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          _ASM_PTR startup_xen)
+#endif
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,
 		.ascii "!writable_page_tables|pae_pgdir_above_4gb")

arch/x86/xen/xen-ops.h

···
 
 bool xen_vcpu_stolen(int vcpu);
 
+extern int xen_have_vcpu_info_placement;
+
 void xen_vcpu_setup(int cpu);
 void xen_setup_vcpu_info_placement(void);
 
···
 __visible void xen_adjust_exception_frame(void);
 
 extern int xen_panic_handler_init(void);
+
+int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int),
+		    int (*cpu_dead_cb)(unsigned int));
+
+void xen_pin_vcpu(int cpu);
+
+void xen_emergency_restart(void);
+#ifdef CONFIG_XEN_PV
+void xen_pv_pre_suspend(void);
+void xen_pv_post_suspend(int suspend_cancelled);
+#else
+static inline void xen_pv_pre_suspend(void) {}
+static inline void xen_pv_post_suspend(int suspend_cancelled) {}
+#endif
+
+#ifdef CONFIG_XEN_PVHVM
+void xen_hvm_post_suspend(int suspend_cancelled);
+#else
+static inline void xen_hvm_post_suspend(int suspend_cancelled) {}
+#endif
 
 #endif /* XEN_OPS_H */

drivers/scsi/xen-scsifront.c

···
 
 	if (seg_grants) {
 		page = virt_to_page(seg);
-		off = (unsigned long)seg & ~PAGE_MASK;
+		off = offset_in_page(seg);
 		len = sizeof(struct scsiif_request_segment) * data_grants;
 		while (len > 0) {
 			bytes = min_t(unsigned int, len, PAGE_SIZE - off);

drivers/xen/balloon.c

···
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
+#ifdef CONFIG_XEN_PV
 static void __init balloon_add_region(unsigned long start_pfn,
 				      unsigned long pages)
 {
···
 
 	balloon_stats.total_pages += extra_pfn_end - start_pfn;
 }
+#endif
 
 static int __init balloon_init(void)
 {
-	int i;
-
 	if (!xen_domain())
 		return -ENODEV;
 
 	pr_info("Initialising balloon driver\n");
 
+#ifdef CONFIG_XEN_PV
 	balloon_stats.current_pages = xen_pv_domain()
 		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
 		: get_num_physpages();
+#else
+	balloon_stats.current_pages = get_num_physpages();
+#endif
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
···
 	register_sysctl_table(xen_root);
 #endif
 
-	/*
-	 * Initialize the balloon with pages from the extra memory
-	 * regions (see arch/x86/xen/setup.c).
-	 */
-	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
-		if (xen_extra_mem[i].n_pfns)
-			balloon_add_region(xen_extra_mem[i].start_pfn,
-					   xen_extra_mem[i].n_pfns);
+#ifdef CONFIG_XEN_PV
+	{
+		int i;
+
+		/*
+		 * Initialize the balloon with pages from the extra memory
+		 * regions (see arch/x86/xen/setup.c).
+		 */
+		for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
+			if (xen_extra_mem[i].n_pfns)
+				balloon_add_region(xen_extra_mem[i].start_pfn,
+						   xen_extra_mem[i].n_pfns);
+	}
+#endif
 
 	return 0;
 }

drivers/xen/efi.c

···
 #include <xen/interface/xen.h>
 #include <xen/interface/platform.h>
 #include <xen/xen.h>
+#include <xen/xen-ops.h>
 
 #include <asm/page.h>
 
···
 	return efi_data(op).status;
 }
 EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps);
+
+void xen_efi_reset_system(int reset_type, efi_status_t status,
+			  unsigned long data_size, efi_char16_t *data)
+{
+	switch (reset_type) {
+	case EFI_RESET_COLD:
+	case EFI_RESET_WARM:
+		xen_reboot(SHUTDOWN_reboot);
+		break;
+	case EFI_RESET_SHUTDOWN:
+		xen_reboot(SHUTDOWN_poweroff);
+		break;
+	default:
+		BUG();
+	}
+}
+EXPORT_SYMBOL_GPL(xen_efi_reset_system);

drivers/xen/events/events_base.c

···
 	if (!VALID_EVTCHN(evtchn))
 		return -1;
 
+	if (!xen_support_evtchn_rebind())
+		return -1;
+
 	/* Send future instances of this interrupt to other vcpu. */
 	bind_vcpu.port = evtchn;
 	bind_vcpu.vcpu = xen_vcpu_nr(tcpu);
···
 	int rc;
 	uint64_t callback_via;
 
-	callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR);
-	rc = xen_set_callback_via(callback_via);
-	BUG_ON(rc);
-	pr_info("Xen HVM callback vector for event delivery is enabled\n");
-	/* in the restore case the vector has already been allocated */
-	if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors))
-		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
-				xen_hvm_callback_vector);
+	if (xen_have_vector_callback) {
+		callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR);
+		rc = xen_set_callback_via(callback_via);
+		if (rc) {
+			pr_err("Request for Xen HVM callback vector failed\n");
+			xen_have_vector_callback = 0;
+			return;
+		}
+		pr_info("Xen HVM callback vector for event delivery is enabled\n");
+		/* in the restore case the vector has already been allocated */
+		if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors))
+			alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
+					xen_hvm_callback_vector);
+	}
 }
 #else
 void xen_callback_vector(void) {}

drivers/xen/platform-pci.c

···
 static int platform_pci_resume(struct pci_dev *pdev)
 {
 	int err;
-	if (!xen_pv_domain())
+
+	if (xen_have_vector_callback)
 		return 0;
+
 	err = xen_set_callback_via(callback_via);
 	if (err) {
 		dev_err(&pdev->dev, "platform_pci_resume failure!\n");
···
 
 	platform_mmio = mmio_addr;
 	platform_mmiolen = mmio_len;
-
-	/* 
-	 * Xen HVM guests always use the vector callback mechanism.
-	 * L1 Dom0 in a nested Xen environment is a PV guest inside in an
-	 * HVM environment. It needs the platform-pci driver to get
-	 * notifications from L0 Xen, but it cannot use the vector callback
-	 * as it is not exported by L1 Xen.
-	 */
-	if (xen_pv_domain()) {
+	if (!xen_have_vector_callback) {
 		ret = xen_allocate_irq(pdev);
 		if (ret) {
 			dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);

drivers/xen/swiotlb-xen.c

···
 		     unsigned long attrs)
 {
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-	if (__generic_dma_ops(dev)->mmap)
-		return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+	if (xen_get_dma_ops(dev)->mmap)
+		return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr,
 						    dma_addr, size, attrs);
 #endif
 	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
···
 			unsigned long attrs)
 {
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-	if (__generic_dma_ops(dev)->get_sgtable) {
+	if (xen_get_dma_ops(dev)->get_sgtable) {
 #if 0
 	/*
 	 * This check verifies that the page belongs to the current domain and
···
 		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
 		BUG_ON (!page_is_ram(bfn));
 #endif
-		return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
+		return xen_get_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
 							   handle, size, attrs);
 	}
 #endif

include/xen/arm/page-coherent.h

···
 #define _ASM_ARM_XEN_PAGE_COHERENT_H
 
 #include <asm/page.h>
+#include <asm/dma-mapping.h>
 #include <linux/dma-mapping.h>
+
+static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dev_dma_ops)
+		return dev->archdata.dev_dma_ops;
+	return get_arch_dma_ops(NULL);
+}
 
 void __xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
···
 static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
 {
-	return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+	return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
 }
 
 static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
 		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
 {
-	__generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+	xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
 }
 
 static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
···
 	 * specific function.
 	 */
 	if (local)
-		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+		xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 	else
 		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
 }
···
 	 * specific function.
 	 */
 	if (pfn_valid(pfn)) {
-		if (__generic_dma_ops(hwdev)->unmap_page)
-			__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+		if (xen_get_dma_ops(hwdev)->unmap_page)
+			xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
 	} else
 		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
 }
···
 {
 	unsigned long pfn = PFN_DOWN(handle);
 	if (pfn_valid(pfn)) {
-		if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
-			__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+		if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
+			xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
 	} else
 		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
 }
···
 {
 	unsigned long pfn = PFN_DOWN(handle);
 	if (pfn_valid(pfn)) {
-		if (__generic_dma_ops(hwdev)->sync_single_for_device)
-			__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+		if (xen_get_dma_ops(hwdev)->sync_single_for_device)
+			xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
 	} else
 		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
 }

include/xen/interface/io/9pfs.h

···
+/*
+ * 9pfs.h -- Xen 9PFS transport
+ *
+ * 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) 2017 Stefano Stabellini <[e-mail]>
+ */
+
+#ifndef __XEN_PUBLIC_IO_9PFS_H__
+#define __XEN_PUBLIC_IO_9PFS_H__
+
+#include "xen/interface/io/ring.h"
+
+/*
+ * See docs/misc/9pfs.markdown in xen.git for the full specification:
+ * https://xenbits.xen.org/docs/unstable/misc/9pfs.html
+ */
+DEFINE_XEN_FLEX_RING_AND_INTF(xen_9pfs);
+
+#endif

include/xen/interface/io/displif.h

···
+/******************************************************************************
+ * displif.h
+ *
+ * Unified display device I/O interface for Xen guest OSes.
+ *
+ * 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) 2016-2017 EPAM Systems Inc.
+ *
+ * Authors: Oleksandr Andrushchenko <[e-mail]>
+ *          Oleksandr Grytsov <[e-mail]>
+ */
+
+#ifndef __XEN_PUBLIC_IO_DISPLIF_H__
+#define __XEN_PUBLIC_IO_DISPLIF_H__
+
+#include "ring.h"
+#include "../grant_table.h"
+
+/*
+ ******************************************************************************
+ *                           Protocol version
+ ******************************************************************************
+ */
+#define XENDISPL_PROTOCOL_VERSION	"1"
+
+/*
+ ******************************************************************************
+ *                  Main features provided by the protocol
+ ******************************************************************************
+ * This protocol aims to provide a unified protocol which fits more
+ * sophisticated use-cases than a framebuffer device can handle. At the
+ * moment basic functionality is supported with the intention to be extended:
+ *  o multiple dynamically allocated/destroyed framebuffers
+ *  o buffers of arbitrary sizes
+ *  o buffer allocation at either back or front end
+ *  o better configuration options including multiple display support
+ *
+ * Note: existing fbif can be used together with displif running at the
+ * same time, e.g. on Linux one provides framebuffer and another DRM/KMS
+ *
+ * Note: display resolution (XenStore's "resolution" property) defines
+ * visible area of the virtual display. At the same time resolution of
+ * the display and frame buffers may differ: buffers can be smaller, equal
+ * or bigger than the visible area. This is to enable use-cases, where backend
+ * may do some post-processing of the display and frame buffers supplied,
+ * e.g. those buffers can be just a part of the final composition.
+ *
+ ******************************************************************************
+ *                        Direction of improvements
+ ******************************************************************************
+ * Future extensions to the existing protocol may include:
+ *  o display/connector cloning
+ *  o allocation of objects other than display buffers
+ *  o plane/overlay support
+ *  o scaling support
+ *  o rotation support
+ *
+ ******************************************************************************
+ *                  Feature and Parameter Negotiation
+ ******************************************************************************
+ *
+ * Front->back notifications: when enqueuing a new request, sending a
+ * notification can be made conditional on xendispl_req (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Backends must set
+ * xendispl_req 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 xendispl_resp (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Frontends must set
+ * xendispl_resp appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()).
+ *
+ * The two halves of a para-virtual display driver utilize nodes within
+ * XenStore to communicate capabilities and to negotiate operating parameters.
+ * This section enumerates these nodes which reside in the respective front and
+ * backend portions of XenStore, following the XenBus convention.
+ *
+ * All data in XenStore is stored as strings. Nodes specifying numeric
+ * values are encoded in decimal. Integer value ranges listed below are
+ * expressed as fixed sized integer types capable of storing the conversion
+ * of a properly formated node string, without loss of information.
+ *
+ ******************************************************************************
+ *                        Example configuration
+ ******************************************************************************
+ *
+ * Note: depending on the use-case backend can expose more display connectors
+ * than the underlying HW physically has by employing SW graphics compositors
+ *
+ * This is an example of backend and frontend configuration:
+ *
+ *--------------------------------- Backend -----------------------------------
+ *
+ * /local/domain/0/backend/vdispl/1/0/frontend-id = "1"
+ * /local/domain/0/backend/vdispl/1/0/frontend = "/local/domain/1/device/vdispl/0"
+ * /local/domain/0/backend/vdispl/1/0/state = "4"
+ * /local/domain/0/backend/vdispl/1/0/versions = "1,2"
+ *
+ *--------------------------------- Frontend ----------------------------------
+ *
+ * /local/domain/1/device/vdispl/0/backend-id = "0"
+ * /local/domain/1/device/vdispl/0/backend = "/local/domain/0/backend/vdispl/1/0"
+ * /local/domain/1/device/vdispl/0/state = "4"
+ * /local/domain/1/device/vdispl/0/version = "1"
+ * /local/domain/1/device/vdispl/0/be-alloc = "1"
+ *
+ *-------------------------- Connector 0 configuration ------------------------
+ *
+ * /local/domain/1/device/vdispl/0/0/resolution = "1920x1080"
+ * /local/domain/1/device/vdispl/0/0/req-ring-ref = "2832"
+ * /local/domain/1/device/vdispl/0/0/req-event-channel = "15"
+ * /local/domain/1/device/vdispl/0/0/evt-ring-ref = "387"
+ * /local/domain/1/device/vdispl/0/0/evt-event-channel = "16"
+ *
+ *-------------------------- Connector 1 configuration ------------------------
+ *
+ * /local/domain/1/device/vdispl/0/1/resolution = "800x600"
+ * /local/domain/1/device/vdispl/0/1/req-ring-ref = "2833"
+ * /local/domain/1/device/vdispl/0/1/req-event-channel = "17"
+ * /local/domain/1/device/vdispl/0/1/evt-ring-ref = "388"
+ * /local/domain/1/device/vdispl/0/1/evt-event-channel = "18"
+ *
+ ******************************************************************************
+ *                            Backend XenBus Nodes
+ ******************************************************************************
+ *
+ *----------------------------- Protocol version ------------------------------
+ *
+ * versions
+ *      Values:         <string>
+ *
+ *      List of XENDISPL_LIST_SEPARATOR separated protocol versions supported
+ *      by the backend. For example "1,2,3".
+ *
+ ******************************************************************************
+ *                            Frontend XenBus Nodes
+ ******************************************************************************
+ *
+ *-------------------------------- Addressing ---------------------------------
+ *
+ * dom-id
+ *      Values:         <uint16_t>
+ *
+ *      Domain identifier.
+ *
+ * dev-id
+ *      Values:         <uint16_t>
+ *
+ *      Device identifier.
+ *
+ * conn-idx
+ *      Values:         <uint8_t>
+ *
+ *      Zero based contigous index of the connector.
+ *      /local/domain/<dom-id>/device/vdispl/<dev-id>/<conn-idx>/...
+ *
+ *----------------------------- Protocol version ------------------------------
+ *
+ * version
+ *      Values:         <string>
+ *
+ *      Protocol version, chosen among the ones supported by the backend.
+ *
+ *------------------------- Backend buffer allocation -------------------------
+ *
+ * be-alloc
+ *      Values:         "0", "1"
+ *
+ *      If value is set to "1", then backend can be a buffer provider/allocator
+ *      for this domain during XENDISPL_OP_DBUF_CREATE operation (see below
+ *      for negotiation).
+ *      If value is not "1" or omitted frontend must allocate buffers itself.
+ *
+ *----------------------------- Connector settings ----------------------------
+ *
+ * resolution
+ *      Values:         <width, uint32_t>x<height, uint32_t>
+ *
+ *      Width and height of the connector in pixels separated by
+ *      XENDISPL_RESOLUTION_SEPARATOR. This defines visible area of the
+ *      display.
+ *
+ *------------------ Connector Request Transport Parameters -------------------
+ *
+ * This communication path is used to deliver requests from frontend to backend
+ * and get the corresponding responses from backend to frontend,
+ * set up per connector.
+ *
+ * req-event-channel
+ *      Values:         <uint32_t>
+ *
+ *      The identifier of the Xen connector's control event channel
+ *      used to signal activity in the ring buffer.
+ *
+ * req-ring-ref
+ *      Values:         <uint32_t>
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      a sole page of connector's control ring buffer.
+ *
+ *------------------- Connector Event Transport Parameters --------------------
+ *
+ * This communication path is used to deliver asynchronous events from backend
+ * to frontend, set up per connector.
+ *
+ * evt-event-channel
+ *      Values:         <uint32_t>
+ *
+ *      The identifier of the Xen connector's event channel
+ *      used to signal activity in the ring buffer.
+ *
+ * evt-ring-ref
+ *      Values:         <uint32_t>
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      a sole page of connector's event ring buffer.
+ */
+
+/*
+ ******************************************************************************
+ *                               STATE DIAGRAMS
+ ******************************************************************************
+ *
+ * Tool stack creates front and back state nodes with initial state
+ * XenbusStateInitialising.
+ * Tool stack creates and sets up frontend display configuration
+ * nodes per domain.
+ *
+ *-------------------------------- Normal flow --------------------------------
+ *
+ * Front                                Back
+ * =================================    =====================================
+ * XenbusStateInitialising              XenbusStateInitialising
+ *                                       o Query backend device identification
+ *                                         data.
+ *                                       o Open and validate backend device.
+ *                                                |
+ *                                                |
+ *                                                V
+ *                                      XenbusStateInitWait
+ *
+ * o Query frontend configuration
+ * o Allocate and initialize
+ *   event channels per configured
+ *   connector.
+ * o Publish transport parameters
+ *   that will be in effect during
+ *   this connection.
+ *              |
+ *              |
+ *              V
+ * XenbusStateInitialised
+ *
+ *                                       o Query frontend transport parameters.
+ *                                       o Connect to the event channels.
+ *                                                |
+ *                                                |
+ *                                                V
+ *                                      XenbusStateConnected
+ *
+ *  o Create and initialize OS
+ *    virtual display connectors
+ *    as per configuration.
+ *              |
+ *              |
+ *              V
+ * XenbusStateConnected
+ *
+ *                                      XenbusStateUnknown
+ *                                      XenbusStateClosed
+ *                                      XenbusStateClosing
+ * o Remove virtual display device
+ * o Remove event channels
+ *              |
+ *              |
+ *              V
+ * XenbusStateClosed
+ *
+ *------------------------------- Recovery flow -------------------------------
+ *
+ * In case of frontend unrecoverable errors backend handles that as
+ * if frontend goes into the XenbusStateClosed state.
+ *
+ * In case of backend unrecoverable errors frontend tries removing
+ * the virtualized device. If this is possible at the moment of error,
+ * then frontend goes into the XenbusStateInitialising state and is ready for
+ * new connection with backend. If the virtualized device is still in use and
+ * cannot be removed, then frontend goes into the XenbusStateReconfiguring state
+ * until either the virtualized device is removed or backend initiates a new
+ * connection. On the virtualized device removal frontend goes into the
+ * XenbusStateInitialising state.
+ *
+ * Note on XenbusStateReconfiguring state of the frontend: if backend has
+ * unrecoverable errors then frontend cannot send requests to the backend
+ * and thus cannot provide functionality of the virtualized device anymore.
+ * After backend is back to normal the virtualized device may still hold some
+ * state: configuration in use, allocated buffers, client application state etc.
+ * In most cases, this will require frontend to implement complex recovery
+ * reconnect logic. Instead, by going into XenbusStateReconfiguring state,
+ * frontend will make sure no new clients of the virtualized device are
+ * accepted, allow existing client(s) to exit gracefully by signaling error
+ * state etc.
+ * Once all the clients are gone frontend can reinitialize the virtualized
+ * device and get into XenbusStateInitialising state again signaling the
+ * backend that a new connection can be made.
+ *
+ * There are multiple conditions possible under which frontend will go from
+ * XenbusStateReconfiguring into XenbusStateInitialising, some of them are OS
+ * specific. For example:
+ * 1. The underlying OS framework may provide callbacks to signal that the last
+ *    client of the virtualized device has gone and the device can be removed
+ * 2. Frontend can schedule a deferred work (timer/tasklet/workqueue)
+ *    to periodically check if this is the right time to re-try removal of
+ *    the virtualized device.
+ * 3. By any other means.
+ *
+ ******************************************************************************
+ *                             REQUEST CODES
+ ******************************************************************************
+ * Request codes [0; 15] are reserved and must not be used
+ */
+
+#define XENDISPL_OP_DBUF_CREATE		0x10
+#define XENDISPL_OP_DBUF_DESTROY	0x11
+#define XENDISPL_OP_FB_ATTACH		0x12
+#define XENDISPL_OP_FB_DETACH		0x13
+#define XENDISPL_OP_SET_CONFIG		0x14
+#define XENDISPL_OP_PG_FLIP		0x15
+
+/*
+ ******************************************************************************
+ *                                 EVENT CODES
+ ******************************************************************************
+ */
+#define XENDISPL_EVT_PG_FLIP		0x00
+
+/*
+ ******************************************************************************
+ *               XENSTORE FIELD AND PATH NAME STRINGS, HELPERS
+ ******************************************************************************
+ */
+#define XENDISPL_DRIVER_NAME		"vdispl"
+
+#define XENDISPL_LIST_SEPARATOR		","
+#define XENDISPL_RESOLUTION_SEPARATOR	"x"
+
+#define XENDISPL_FIELD_BE_VERSIONS	"versions"
+#define XENDISPL_FIELD_FE_VERSION	"version"
+#define XENDISPL_FIELD_REQ_RING_REF	"req-ring-ref"
+#define XENDISPL_FIELD_REQ_CHANNEL	"req-event-channel"
+#define XENDISPL_FIELD_EVT_RING_REF	"evt-ring-ref"
+#define XENDISPL_FIELD_EVT_CHANNEL	"evt-event-channel"
+#define XENDISPL_FIELD_RESOLUTION	"resolution"
+#define XENDISPL_FIELD_BE_ALLOC		"be-alloc"
+
+/*
+ ******************************************************************************
+ *                          STATUS RETURN CODES
+ ******************************************************************************
+ *
+ * Status return code is zero on success and -XEN_EXX on failure.
+ *
+ ******************************************************************************
+ *                              Assumptions
+ ******************************************************************************
+ * o usage of grant reference 0 as invalid grant reference:
+ *   grant reference 0 is valid, but never exposed to a PV driver,
+ *   because of the fact it is already in use/reserved by the PV console.
+ * o all references in this document to page sizes must be treated
+ *   as pages of size XEN_PAGE_SIZE unless otherwise noted.
+ *
+ ******************************************************************************
+ *       Description of the protocol between frontend and backend driver
+ ******************************************************************************
+ *
+ * The two halves of a Para-virtual display driver communicate with
+ * each other using shared pages and event channels.
+ * Shared page contains a ring with request/response packets.
+ *
+ * All reserved fields in the structures below must be 0.
+ * Display buffers's cookie of value 0 is treated as invalid.
+ * Framebuffer's cookie of value 0 is treated as invalid.
+ *
+ * For all request/response/event packets that use cookies:
+ *   dbuf_cookie - uint64_t, unique to guest domain value used by the backend
+ *     to map remote display buffer to its local one
+ *   fb_cookie - uint64_t, unique to guest domain value used by the backend
+ *     to map remote framebuffer to its local one
+ *
+ *---------------------------------- Requests ---------------------------------
+ *
+ * All requests/responses, which are not connector specific, must be sent over
+ * control ring of the connector which has the index value of 0:
+ *   /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref
+ *
+ * All request packets have the same length (64 octets)
+ * All request packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |    operation   |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ *   id - uint16_t, private guest value, echoed in response
+ *   operation - uint8_t, operation code, XENDISPL_OP_???
+ *
+ * Request dbuf creation - request creation of a display buffer.
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |_OP_DBUF_CREATE |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie low 32-bit                      | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie high 32-bit                     | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                               width                               | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                               height                              | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                                bpp                                | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                             buffer_sz                             | 32
+ * +----------------+----------------+----------------+----------------+
+ * |                               flags                               | 36
+ * +----------------+----------------+----------------+----------------+
+ * |                           gref_directory                          | 40
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 44
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Must be sent over control ring of the connector which has the index
+ * value of 0:
+ *   /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref
+ * All unused bits in flags field must be set to 0.
+ *
+ * An attempt to create multiple display buffers with the same dbuf_cookie is
+ * an error. dbuf_cookie can be re-used after destroying the corresponding
+ * display buffer.
+ *
+ * Width and height of the display buffers can be smaller, equal or bigger
+ * than the connector's resolution. Depth/pixel format of the individual
+ * buffers can differ as well.
+ *
+ * width - uint32_t, width in pixels
+ * height - uint32_t, height in pixels
+ * bpp - uint32_t, bits per pixel
+ * buffer_sz - uint32_t, buffer size to be allocated, octets
+ * flags - uint32_t, flags of the operation
+ *   o XENDISPL_DBUF_FLG_REQ_ALLOC - if set, then backend is requested
+ *     to allocate the buffer with the parameters provided in this request.
+ *     Page directory is handled as follows:
+ *       Frontend on request:
+ *         o allocates pages for the directory (gref_directory,
+ *           gref_dir_next_page(s)
+ *         o grants permissions for the pages of the directory to the backend
+ *         o sets gref_dir_next_page fields
+ *       Backend on response:
+ *         o grants permissions for the pages of the buffer allocated to
+ *           the frontend
+ *         o fills in page directory with grant references
+ *           (gref[] in struct xendispl_page_directory)
+ * gref_directory - grant_ref_t, a reference to the first shared page
+ *   describing shared buffer references. At least one page exists. If shared
+ *   buffer size (buffer_sz) exceeds what can be addressed by this single page,
+ *   then reference to the next page must be supplied (see gref_dir_next_page
+ *   below)
+ */
+
+#define XENDISPL_DBUF_FLG_REQ_ALLOC	(1 << 0)
+
+struct xendispl_dbuf_create_req {
+	uint64_t dbuf_cookie;
+	uint32_t width;
+	uint32_t height;
+	uint32_t bpp;
+	uint32_t buffer_sz;
+	uint32_t flags;
+	grant_ref_t gref_directory;
+};
+
+/*
+ * Shared page for XENDISPL_OP_DBUF_CREATE buffer descriptor (gref_directory in
+ * the request) employs a list of pages, describing all pages of the shared
+ * data buffer:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |                        gref_dir_next_page                         | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              gref[0]                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                              gref[i]                              | i*4+8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             gref[N - 1]                           | N*4+8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * gref_dir_next_page - grant_ref_t, reference to the next page describing
+ *   page directory. Must be 0 if there are no more pages in the list.
+ * gref[i] - grant_ref_t, reference to a shared page of the buffer
+ *   allocated at XENDISPL_OP_DBUF_CREATE
+ *
+ * Number of grant_ref_t entries in the whole page directory is not
+ * passed, but instead can be calculated as:
+ *   num_grefs_total = (XENDISPL_OP_DBUF_CREATE.buffer_sz + XEN_PAGE_SIZE - 1) /
+ *       XEN_PAGE_SIZE
+ */
+
+struct xendispl_page_directory {
+	grant_ref_t gref_dir_next_page;
+	grant_ref_t gref[1]; /* Variable length */
+};
+
+/*
+ * Request dbuf destruction - destroy a previously allocated display buffer:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |_OP_DBUF_DESTROY|   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie low 32-bit                      | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie high 32-bit                     | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Must be sent over control ring of the connector which has the index
+ * value of 0:
+ *   /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref
+ */
+
+struct xendispl_dbuf_destroy_req {
+	uint64_t dbuf_cookie;
+};
+
+/*
+ * Request framebuffer attachment - request attachment of a framebuffer to
+ * previously created display buffer.
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                | _OP_FB_ATTACH  |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie low 32-bit                      | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                       dbuf_cookie high 32-bit                     | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie low 32-bit                       | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie high 32-bit                      | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                               width                               | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                               height                              | 32
+ * +----------------+----------------+----------------+----------------+
+ * |                            pixel_format                           | 36
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Must be sent over control ring of the connector which has the index
+ * value of 0:
+ *   /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref
+ * Width and height can be smaller, equal or bigger than the connector's
+ * resolution.
+ *
+ * An attempt to create multiple frame buffers with the same fb_cookie is
+ * an error. fb_cookie can be re-used after destroying the corresponding
+ * frame buffer.
+ *
+ * width - uint32_t, width in pixels
+ * height - uint32_t, height in pixels
+ * pixel_format - uint32_t, pixel format of the framebuffer, FOURCC code
+ */
+
+struct xendispl_fb_attach_req {
+	uint64_t dbuf_cookie;
+	uint64_t fb_cookie;
+	uint32_t width;
+	uint32_t height;
+	uint32_t pixel_format;
+};
+
+/*
+ * Request framebuffer detach - detach a previously
+ * attached framebuffer from the display buffer in request:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |  _OP_FB_DETACH |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Must be sent over control ring of the connector which has the index
+ * value of 0:
+ *   /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref
+ */
+
+struct xendispl_fb_detach_req {
+	uint64_t fb_cookie;
+};
+
+/*
+ * Request configuration set/reset - request to set or reset
+ * the configuration/mode of the display:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                | _OP_SET_CONFIG |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                                 x                                 | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                                 y                                 | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                               width                               | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                               height                              | 32
+ * +----------------+----------------+----------------+----------------+
+ * |                                bpp                                | 40
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 44
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Pass all zeros to reset, otherwise command is treated as
+ * configuration set.
+ * Framebuffer's cookie defines which framebuffer/dbuf must be
+ * displayed while enabling display (applying configuration).
+ * x, y, width and height are bound by the connector's resolution and must not
+ * exceed it.
+ *
+ * x - uint32_t, starting position in pixels by X axis
+ * y - uint32_t, starting position in pixels by Y axis
+ * width - uint32_t, width in pixels
+ * height - uint32_t, height in pixels
+ * bpp - uint32_t, bits per pixel
+ */
+
+struct xendispl_set_config_req {
+	uint64_t fb_cookie;
+	uint32_t x;
+	uint32_t y;
+	uint32_t width;
+	uint32_t height;
+	uint32_t bpp;
+};
+
+/*
+ * Request page flip - request to flip a page identified by the framebuffer
+ * cookie:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                | _OP_PG_FLIP    |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ */
+
+struct xendispl_page_flip_req {
+	uint64_t fb_cookie;
+};
+
+/*
+ *---------------------------------- Responses --------------------------------
+ *
+ * All response packets have the same length (64 octets)
+ *
+ * All response packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |            reserved             | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              status                               | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 12
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * id - uint16_t, private guest value, echoed from request
+ * status - int32_t, response status, zero on success and -XEN_EXX on failure
+ *
+ *----------------------------------- Events ----------------------------------
+ *
+ * Events are sent via a shared page allocated by the front and propagated by
+ *   evt-event-channel/evt-ring-ref XenStore entries
+ * All event packets have the same length (64 octets)
+ * All event packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |      type      |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * id - uint16_t, event id, may be used by front
+ * type - uint8_t, type of the event
+ *
+ *
+ * Page flip complete event - event from back to front on page flip completed:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   _EVT_PG_FLIP |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                        fb_cookie high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ */
+
+struct xendispl_pg_flip_evt {
+	uint64_t fb_cookie;
+};
+
+struct xendispl_req {
+	uint16_t id;
+	uint8_t operation;
+	uint8_t reserved[5];
+	union {
+		struct xendispl_dbuf_create_req dbuf_create;
+		struct xendispl_dbuf_destroy_req dbuf_destroy;
+		struct xendispl_fb_attach_req fb_attach;
+		struct xendispl_fb_detach_req fb_detach;
+		struct xendispl_set_config_req set_config;
+		struct xendispl_page_flip_req pg_flip;
+		uint8_t reserved[56];
+	} op;
+};
+
+struct xendispl_resp {
+	uint16_t id;
+	uint8_t operation;
+	uint8_t reserved;
+	int32_t status;
+	uint8_t reserved1[56];
+};
+
+struct xendispl_evt {
+	uint16_t id;
+	uint8_t type;
+	uint8_t reserved[5];
+	union {
+		struct xendispl_pg_flip_evt pg_flip;
+		uint8_t reserved[56];
+	} op;
+};
+
+DEFINE_RING_TYPES(xen_displif, struct xendispl_req, struct xendispl_resp);
+
+/*
+ ******************************************************************************
+ *                        Back to front events delivery
+ ******************************************************************************
+ * In order to deliver asynchronous events from back to front a shared page is
+ * allocated by front and its granted reference propagated to back via
+ * XenStore entries (evt-ring-ref/evt-event-channel).
+ * This page has a common header used by both front and back to synchronize
+ * access and control event's ring buffer, while back being a producer of the
+ * events and front being a consumer. The rest of the page after the header
+ * is used for event packets.
+ *
+ * Upon reception of an event(s) front may confirm its reception
+ * for either each event, group of events or none.
+ */
+
+struct xendispl_event_page {
+	uint32_t in_cons;
+	uint32_t in_prod;
+	uint8_t reserved[56];
+};
+
+#define XENDISPL_EVENT_PAGE_SIZE XEN_PAGE_SIZE
+#define XENDISPL_IN_RING_OFFS (sizeof(struct xendispl_event_page))
+#define XENDISPL_IN_RING_SIZE (XENDISPL_EVENT_PAGE_SIZE - XENDISPL_IN_RING_OFFS)
+#define XENDISPL_IN_RING_LEN (XENDISPL_IN_RING_SIZE / sizeof(struct xendispl_evt))
+#define XENDISPL_IN_RING(page) \
+	((struct xendispl_evt *)((char *)(page) + XENDISPL_IN_RING_OFFS))
+#define XENDISPL_IN_RING_REF(page, idx) \
+	(XENDISPL_IN_RING((page))[(idx) % XENDISPL_IN_RING_LEN])
+
+#endif /* __XEN_PUBLIC_IO_DISPLIF_H__ */

include/xen/interface/io/kbdif.h

···
 #ifndef __XEN_PUBLIC_IO_KBDIF_H__
 #define __XEN_PUBLIC_IO_KBDIF_H__
 
-/* In events (backend -> frontend) */
+/*
+ *****************************************************************************
+ *                     Feature and Parameter Negotiation
+ *****************************************************************************
+ *
+ * The two halves of a para-virtual driver utilize nodes within
+ * XenStore to communicate capabilities and to negotiate operating parameters.
+ * This section enumerates these nodes which reside in the respective front and
+ * backend portions of XenStore, following XenBus convention.
+ *
+ * All data in XenStore is stored as strings.  Nodes specifying numeric
+ * values are encoded in decimal. Integer value ranges listed below are
+ * expressed as fixed sized integer types capable of storing the conversion
+ * of a properly formated node string, without loss of information.
+ *
+ *****************************************************************************
+ *                            Backend XenBus Nodes
+ *****************************************************************************
+ *
+ *---------------------------- Features supported ----------------------------
+ *
+ * Capable backend advertises supported features by publishing
+ * corresponding entries in XenStore and puts 1 as the value of the entry.
+ * If a feature is not supported then 0 must be set or feature entry omitted.
+ *
+ * feature-abs-pointer
+ *      Values:         <uint>
+ *
+ *      Backends, which support reporting of absolute coordinates for pointer
+ *      device should set this to 1.
+ *
+ * feature-multi-touch
+ *      Values:         <uint>
+ *
+ *      Backends, which support reporting of multi-touch events
+ *      should set this to 1.
+ *
+ *------------------------- Pointer Device Parameters ------------------------
+ *
+ * width
+ *      Values:         <uint>
+ *
+ *      Maximum X coordinate (width) to be used by the frontend
+ *      while reporting input events, pixels, [0; UINT32_MAX].
+ *
+ * height
+ *      Values:         <uint>
+ *
+ *      Maximum Y coordinate (height) to be used by the frontend
+ *      while reporting input events, pixels, [0; UINT32_MAX].
+ *
+ *****************************************************************************
+ *                            Frontend XenBus Nodes
+ *****************************************************************************
+ *
+ *------------------------------ Feature request -----------------------------
+ *
+ * Capable frontend requests features from backend via setting corresponding
+ * entries to 1 in XenStore. Requests for features not advertised as supported
+ * by the backend have no effect.
+ *
+ * request-abs-pointer
+ *      Values:         <uint>
+ *
+ *      Request backend to report absolute pointer coordinates
+ *      (XENKBD_TYPE_POS) instead of relative ones (XENKBD_TYPE_MOTION).
+ *
+ * request-multi-touch
+ *      Values:         <uint>
+ *
+ *      Request backend to report multi-touch events.
+ *
+ *----------------------- Request Transport Parameters -----------------------
+ *
+ * event-channel
+ *      Values:         <uint>
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * page-gref
+ *      Values:         <uint>
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      a sole page in a single page sized event ring buffer.
+ *
+ * page-ref
+ *      Values:         <uint>
+ *
+ *      OBSOLETE, not recommended for use.
+ *      PFN of the shared page.
+ *
+ *----------------------- Multi-touch Device Parameters -----------------------
+ *
+ * multi-touch-num-contacts
+ *      Values:         <uint>
+ *
+ *      Number of simultaneous touches reported.
+ *
+ * multi-touch-width
+ *      Values:         <uint>
+ *
+ *      Width of the touch area to be used by the frontend
+ *      while reporting input events, pixels, [0; UINT32_MAX].
+ *
+ * multi-touch-height
+ *      Values:         <uint>
+ *
+ *      Height of the touch area to be used by the frontend
+ *      while reporting input events, pixels, [0; UINT32_MAX].
+ */
 
 /*
+ * EVENT CODES.
+ */
+
+#define XENKBD_TYPE_MOTION		1
+#define XENKBD_TYPE_RESERVED		2
+#define XENKBD_TYPE_KEY			3
+#define XENKBD_TYPE_POS			4
+#define XENKBD_TYPE_MTOUCH		5
+
+/* Multi-touch event sub-codes */
+
+#define XENKBD_MT_EV_DOWN		0
+#define XENKBD_MT_EV_UP			1
+#define XENKBD_MT_EV_MOTION		2
+#define XENKBD_MT_EV_SYN		3
+#define XENKBD_MT_EV_SHAPE		4
+#define XENKBD_MT_EV_ORIENT		5
+
+/*
+ * CONSTANTS, XENSTORE FIELD AND PATH NAME STRINGS, HELPERS.
+ */
+
+#define XENKBD_DRIVER_NAME		"vkbd"
+
+#define XENKBD_FIELD_FEAT_ABS_POINTER	"feature-abs-pointer"
+#define XENKBD_FIELD_FEAT_MTOUCH	"feature-multi-touch"
+#define XENKBD_FIELD_REQ_ABS_POINTER	"request-abs-pointer"
+#define XENKBD_FIELD_REQ_MTOUCH		"request-multi-touch"
+#define XENKBD_FIELD_RING_GREF		"page-gref"
+#define XENKBD_FIELD_EVT_CHANNEL	"event-channel"
+#define XENKBD_FIELD_WIDTH		"width"
+#define XENKBD_FIELD_HEIGHT		"height"
+#define XENKBD_FIELD_MT_WIDTH		"multi-touch-width"
+#define XENKBD_FIELD_MT_HEIGHT		"multi-touch-height"
+#define XENKBD_FIELD_MT_NUM_CONTACTS	"multi-touch-num-contacts"
+
+/* OBSOLETE, not recommended for use */
+#define XENKBD_FIELD_RING_REF		"page-ref"
+
+/*
+ *****************************************************************************
+ * Description of the protocol between frontend and backend driver.
+ *****************************************************************************
+ *
+ * The two halves of a Para-virtual driver communicate with
+ * each other using a shared page and an event channel.
+ * Shared page contains a ring with event structures.
+ *
+ * All reserved fields in the structures below must be 0.
+ *
+ *****************************************************************************
+ *                           Backend to frontend events
+ *****************************************************************************
+ *
  * Frontends should ignore unknown in events.
+ * All event packets have the same length (40 octets)
+ * All event packets have common header:
+ *
+ *          0         octet
+ * +-----------------+
+ * |       type      |
+ * +-----------------+
+ * type - uint8_t, event code, XENKBD_TYPE_???
+ *
+ *
+ * Pointer relative movement event
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MOTION  |                     reserved                     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                               rel_x                               | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                               rel_y                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                               rel_z                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * rel_x - int32_t, relative X motion
+ * rel_y - int32_t, relative Y motion
+ * rel_z - int32_t, relative Z motion (wheel)
  */
-
-/* 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) */
+	uint8_t type;
+	int32_t rel_x;
+	int32_t rel_y;
+	int32_t rel_z;
 };
+
+/*
+ * Key event (includes pointer buttons)
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_KEY     |     pressed    |            reserved             | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              keycode                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 12
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * pressed - uint8_t, 1 if pressed; 0 otherwise
+ * keycode - uint32_t, KEY_* from linux/input.h
+ */
 
 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 */
+	uint8_t type;
+	uint8_t pressed;
+	uint32_t keycode;
 };
 
+/*
+ * Pointer absolute position event
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_POS     |                     reserved                     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_x                               | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_y                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                               rel_z                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * abs_x - int32_t, absolute X position (in FB pixels)
+ * abs_y - int32_t, absolute Y position (in FB pixels)
+ * rel_z - int32_t, relative Z motion (wheel)
+ */
+
 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) */
+	uint8_t type;
+	int32_t abs_x;
+	int32_t abs_y;
+	int32_t rel_z;
+};
+
+/*
+ * Multi-touch event and its sub-types
+ *
+ * All multi-touch event packets have common header:
+ *
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |   event_type   |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * event_type - unt8_t, multi-touch event sub-type, XENKBD_MT_EV_???
+ * contact_id - unt8_t, ID of the contact
+ *
+ * Touch interactions can consist of one or more contacts.
+ * For each contact, a series of events is generated, starting
+ * with a down event, followed by zero or more motion events,
+ * and ending with an up event. Events relating to the same
+ * contact point can be identified by the ID of the sequence: contact ID.
+ * Contact ID may be reused after XENKBD_MT_EV_UP event and
+ * is in the [0; XENKBD_FIELD_NUM_CONTACTS - 1] range.
+ *
+ * For further information please refer to documentation on Wayland [1],
+ * Linux [2] and Windows [3] multi-touch support.
+ *
+ * [1] https://cgit.freedesktop.org/wayland/wayland/tree/protocol/wayland.xml
+ * [2] https://www.kernel.org/doc/Documentation/input/multi-touch-protocol.txt
+ * [3] https://msdn.microsoft.com/en-us/library/jj151564(v=vs.85).aspx
+ *
+ *
+ * Multi-touch down event - sent when a new touch is made: touch is assigned
+ * a unique contact ID, sent with this and consequent events related
+ * to this touch.
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |   _MT_EV_DOWN  |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_x                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_y                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * abs_x - int32_t, absolute X position, in pixels
+ * abs_y - int32_t, absolute Y position, in pixels
+ *
+ * Multi-touch contact release event
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |  _MT_EV_UP     |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Multi-touch motion event
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |  _MT_EV_MOTION |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_x                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                               abs_y                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * abs_x - int32_t, absolute X position, in pixels,
+ * abs_y - int32_t, absolute Y position, in pixels,
+ *
+ * Multi-touch input synchronization event - shows end of a set of events
+ * which logically belong together.
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |  _MT_EV_SYN    |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Multi-touch shape event - touch point's shape has changed its shape.
+ * Shape is approximated by an ellipse through the major and minor axis
+ * lengths: major is the longer diameter of the ellipse and minor is the
+ * shorter one. Center of the ellipse is reported via
+ * XENKBD_MT_EV_DOWN/XENKBD_MT_EV_MOTION events.
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |  _MT_EV_SHAPE  |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                               major                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                               minor                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * major - unt32_t, length of the major axis, pixels
+ * minor - unt32_t, length of the minor axis, pixels
+ *
+ * Multi-touch orientation event - touch point's shape has changed
+ * its orientation: calculated as a clockwise angle between the major axis
+ * of the ellipse and positive Y axis in degrees, [-180; +180].
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |  _TYPE_MTOUCH  |  _MT_EV_ORIENT |   contact_id   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |           orientation           |            reserved             | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 16
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 40
+ * +----------------+----------------+----------------+----------------+
+ *
+ * orientation - int16_t, clockwise angle of the major axis
+ */
+
+struct xenkbd_mtouch {
+	uint8_t type;			/* XENKBD_TYPE_MTOUCH */
+	uint8_t event_type;		/* XENKBD_MT_EV_??? */
+	uint8_t contact_id;
+	uint8_t reserved[5];		/* reserved for the future use */
+	union {
+		struct {
+			int32_t abs_x;	/* absolute X position, pixels */
+			int32_t abs_y;	/* absolute Y position, pixels */
+		} pos;
+		struct {
+			uint32_t major;	/* length of the major axis, pixels */
+			uint32_t minor;	/* length of the minor axis, pixels */
+		} shape;
+		int16_t orientation;	/* clockwise angle of the major axis */
+	} u;
 };
 
 #define XENKBD_IN_EVENT_SIZE 40
···
 	struct xenkbd_motion motion;
 	struct xenkbd_key key;
 	struct xenkbd_position pos;
+	struct xenkbd_mtouch mtouch;
 	char pad[XENKBD_IN_EVENT_SIZE];
 };
 
-/* Out events (frontend -> backend) */
-
 /*
+ *****************************************************************************
+ *                            Frontend to backend events
+ *****************************************************************************
+ *
  * 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.
+
+ * All event packets have the same length (40 octets)
+ * All event packets have common header:
+ *          0         octet
+ * +-----------------+
+ * |       type      |
+ * +-----------------+
+ * type - uint8_t, event code
  */
 
 #define XENKBD_OUT_EVENT_SIZE 40
···
 	char pad[XENKBD_OUT_EVENT_SIZE];
 };
 
-/* shared page */
+/*
+ *****************************************************************************
+ *                            Shared page
+ *****************************************************************************
+ */
 
 #define XENKBD_IN_RING_SIZE 2048
 #define XENKBD_IN_RING_LEN (XENKBD_IN_RING_SIZE / XENKBD_IN_EVENT_SIZE)
···
 	uint32_t out_cons, out_prod;
 };
 
-#endif
+#endif /* __XEN_PUBLIC_IO_KBDIF_H__ */

include/xen/interface/io/ring.h

···
     (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r);			\
 } while (0)
 
+
+/*
+ * DEFINE_XEN_FLEX_RING_AND_INTF defines two monodirectional rings and
+ * functions to check if there is data on the ring, and to read and
+ * write to them.
+ *
+ * DEFINE_XEN_FLEX_RING is similar to DEFINE_XEN_FLEX_RING_AND_INTF, but
+ * does not define the indexes page. As different protocols can have
+ * extensions to the basic format, this macro allow them to define their
+ * own struct.
+ *
+ * XEN_FLEX_RING_SIZE
+ *   Convenience macro to calculate the size of one of the two rings
+ *   from the overall order.
+ *
+ * $NAME_mask
+ *   Function to apply the size mask to an index, to reduce the index
+ *   within the range [0-size].
+ *
+ * $NAME_read_packet
+ *   Function to read data from the ring. The amount of data to read is
+ *   specified by the "size" argument.
+ *
+ * $NAME_write_packet
+ *   Function to write data to the ring. The amount of data to write is
+ *   specified by the "size" argument.
+ *
+ * $NAME_get_ring_ptr
+ *   Convenience function that returns a pointer to read/write to the
+ *   ring at the right location.
+ *
+ * $NAME_data_intf
+ *   Indexes page, shared between frontend and backend. It also
+ *   contains the array of grant refs.
+ *
+ * $NAME_queued
+ *   Function to calculate how many bytes are currently on the ring,
+ *   ready to be read. It can also be used to calculate how much free
+ *   space is currently on the ring (XEN_FLEX_RING_SIZE() -
+ *   $NAME_queued()).
+ */
+
+#ifndef XEN_PAGE_SHIFT
+/* The PAGE_SIZE for ring protocols and hypercall interfaces is always
+ * 4K, regardless of the architecture, and page granularity chosen by
+ * operating systems.
+ */
+#define XEN_PAGE_SHIFT 12
+#endif
+#define XEN_FLEX_RING_SIZE(order)                                             \
+    (1UL << ((order) + XEN_PAGE_SHIFT - 1))
+
+#define DEFINE_XEN_FLEX_RING(name)                                            \
+static inline RING_IDX name##_mask(RING_IDX idx, RING_IDX ring_size)          \
+{                                                                             \
+    return idx & (ring_size - 1);                                             \
+}                                                                             \
+                                                                              \
+static inline unsigned char *name##_get_ring_ptr(unsigned char *buf,          \
+                                                 RING_IDX idx,                \
+                                                 RING_IDX ring_size)          \
+{                                                                             \
+    return buf + name##_mask(idx, ring_size);                                 \
+}                                                                             \
+                                                                              \
+static inline void name##_read_packet(void *opaque,                           \
+                                      const unsigned char *buf,               \
+                                      size_t size,                            \
+                                      RING_IDX masked_prod,                   \
+                                      RING_IDX *masked_cons,                  \
+                                      RING_IDX ring_size)                     \
+{                                                                             \
+    if (*masked_cons < masked_prod ||                                         \
+        size <= ring_size - *masked_cons) {                                   \
+        memcpy(opaque, buf + *masked_cons, size);                             \
+    } else {                                                                  \
+        memcpy(opaque, buf + *masked_cons, ring_size - *masked_cons);         \
+        memcpy((unsigned char *)opaque + ring_size - *masked_cons, buf,       \
+               size - (ring_size - *masked_cons));                            \
+    }                                                                         \
+    *masked_cons = name##_mask(*masked_cons + size, ring_size);               \
+}                                                                             \
+                                                                              \
+static inline void name##_write_packet(unsigned char *buf,                    \
+                                       const void *opaque,                    \
+                                       size_t size,                           \
+                                       RING_IDX *masked_prod,                 \
+                                       RING_IDX masked_cons,                  \
+                                       RING_IDX ring_size)                    \
+{                                                                             \
+    if (*masked_prod < masked_cons ||                                         \
+        size <= ring_size - *masked_prod) {                                   \
+        memcpy(buf + *masked_prod, opaque, size);                             \
+    } else {                                                                  \
+        memcpy(buf + *masked_prod, opaque, ring_size - *masked_prod);         \
+        memcpy(buf, (unsigned char *)opaque + (ring_size - *masked_prod),     \
+               size - (ring_size - *masked_prod));                            \
+    }                                                                         \
+    *masked_prod = name##_mask(*masked_prod + size, ring_size);               \
+}                                                                             \
+                                                                              \
+static inline RING_IDX name##_queued(RING_IDX prod,                           \
+                                     RING_IDX cons,                           \
+                                     RING_IDX ring_size)                      \
+{                                                                             \
+    RING_IDX size;                                                            \
+                                                                              \
+    if (prod == cons)                                                         \
+        return 0;                                                             \
+                                                                              \
+    prod = name##_mask(prod, ring_size);                                      \
+    cons = name##_mask(cons, ring_size);                                      \
+                                                                              \
+    if (prod == cons)                                                         \
+        return ring_size;                                                     \
+                                                                              \
+    if (prod > cons)                                                          \
+        size = prod - cons;                                                   \
+    else                                                                      \
+        size = ring_size - (cons - prod);                                     \
+    return size;                                                              \
+}                                                                             \
+                                                                              \
+struct name##_data {                                                          \
+    unsigned char *in; /* half of the allocation */                           \
+    unsigned char *out; /* half of the allocation */                          \
+}
+
+#define DEFINE_XEN_FLEX_RING_AND_INTF(name)                                   \
+struct name##_data_intf {                                                     \
+    RING_IDX in_cons, in_prod;                                                \
+                                                                              \
+    uint8_t pad1[56];                                                         \
+                                                                              \
+    RING_IDX out_cons, out_prod;                                              \
+                                                                              \
+    uint8_t pad2[56];                                                         \
+                                                                              \
+    RING_IDX ring_order;                                                      \
+    grant_ref_t ref[];                                                        \
+};                                                                            \
+DEFINE_XEN_FLEX_RING(name)
+
 #endif /* __XEN_PUBLIC_IO_RING_H__ */

include/xen/interface/io/sndif.h

···
+/******************************************************************************
+ * sndif.h
+ *
+ * Unified sound-device I/O interface for Xen guest OSes.
+ *
+ * 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) 2013-2015 GlobalLogic Inc.
+ * Copyright (C) 2016-2017 EPAM Systems Inc.
+ *
+ * Authors: Oleksandr Andrushchenko <[e-mail]>
+ *          Oleksandr Grytsov <[e-mail]>
+ *          Oleksandr Dmytryshyn <[e-mail]>
+ *          Iurii Konovalenko <[e-mail]>
+ */
+
+#ifndef __XEN_PUBLIC_IO_SNDIF_H__
+#define __XEN_PUBLIC_IO_SNDIF_H__
+
+#include "ring.h"
+#include "../grant_table.h"
+
+/*
+ ******************************************************************************
+ *                  Feature and Parameter Negotiation
+ ******************************************************************************
+ *
+ * Front->back notifications: when enqueuing a new request, sending a
+ * notification can be made conditional on xensnd_req (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Backends must set
+ * xensnd_req 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 xensnd_resp (i.e., the generic
+ * hold-off mechanism provided by the ring macros). Frontends must set
+ * xensnd_resp appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()).
+ *
+ * The two halves of a para-virtual sound card driver utilize nodes within
+ * XenStore to communicate capabilities and to negotiate operating parameters.
+ * This section enumerates these nodes which reside in the respective front and
+ * backend portions of XenStore, following the XenBus convention.
+ *
+ * All data in XenStore is stored as strings. Nodes specifying numeric
+ * values are encoded in decimal. Integer value ranges listed below are
+ * expressed as fixed sized integer types capable of storing the conversion
+ * of a properly formated node string, without loss of information.
+ *
+ ******************************************************************************
+ *                        Example configuration
+ ******************************************************************************
+ *
+ * Note: depending on the use-case backend can expose more sound cards and
+ * PCM devices/streams than the underlying HW physically has by employing
+ * SW mixers, configuring virtual sound streams, channels etc.
+ *
+ * This is an example of backend and frontend configuration:
+ *
+ *--------------------------------- Backend -----------------------------------
+ *
+ * /local/domain/0/backend/vsnd/1/0/frontend-id = "1"
+ * /local/domain/0/backend/vsnd/1/0/frontend = "/local/domain/1/device/vsnd/0"
+ * /local/domain/0/backend/vsnd/1/0/state = "4"
+ * /local/domain/0/backend/vsnd/1/0/versions = "1,2"
+ *
+ *--------------------------------- Frontend ----------------------------------
+ *
+ * /local/domain/1/device/vsnd/0/backend-id = "0"
+ * /local/domain/1/device/vsnd/0/backend = "/local/domain/0/backend/vsnd/1/0"
+ * /local/domain/1/device/vsnd/0/state = "4"
+ * /local/domain/1/device/vsnd/0/version = "1"
+ *
+ *----------------------------- Card configuration ----------------------------
+ *
+ * /local/domain/1/device/vsnd/0/short-name = "Card short name"
+ * /local/domain/1/device/vsnd/0/long-name = "Card long name"
+ * /local/domain/1/device/vsnd/0/sample-rates = "8000,32000,44100,48000,96000"
+ * /local/domain/1/device/vsnd/0/sample-formats = "s8,u8,s16_le,s16_be"
+ * /local/domain/1/device/vsnd/0/buffer-size = "262144"
+ *
+ *------------------------------- PCM device 0 --------------------------------
+ *
+ * /local/domain/1/device/vsnd/0/0/name = "General analog"
+ * /local/domain/1/device/vsnd/0/0/channels-max = "5"
+ *
+ *----------------------------- Stream 0, playback ----------------------------
+ *
+ * /local/domain/1/device/vsnd/0/0/0/type = "p"
+ * /local/domain/1/device/vsnd/0/0/0/sample-formats = "s8,u8"
+ * /local/domain/1/device/vsnd/0/0/0/unique-id = "0"
+ *
+ * /local/domain/1/device/vsnd/0/0/0/ring-ref = "386"
+ * /local/domain/1/device/vsnd/0/0/0/event-channel = "15"
+ *
+ *------------------------------ Stream 1, capture ----------------------------
+ *
+ * /local/domain/1/device/vsnd/0/0/1/type = "c"
+ * /local/domain/1/device/vsnd/0/0/1/channels-max = "2"
+ * /local/domain/1/device/vsnd/0/0/1/unique-id = "1"
+ *
+ * /local/domain/1/device/vsnd/0/0/1/ring-ref = "384"
+ * /local/domain/1/device/vsnd/0/0/1/event-channel = "13"
+ *
+ *------------------------------- PCM device 1 --------------------------------
+ *
+ * /local/domain/1/device/vsnd/0/1/name = "HDMI-0"
+ * /local/domain/1/device/vsnd/0/1/sample-rates = "8000,32000,44100"
+ *
+ *------------------------------ Stream 0, capture ----------------------------
+ *
+ * /local/domain/1/device/vsnd/0/1/0/type = "c"
+ * /local/domain/1/device/vsnd/0/1/0/unique-id = "2"
+ *
+ * /local/domain/1/device/vsnd/0/1/0/ring-ref = "387"
+ * /local/domain/1/device/vsnd/0/1/0/event-channel = "151"
+ *
+ *------------------------------- PCM device 2 --------------------------------
+ *
+ * /local/domain/1/device/vsnd/0/2/name = "SPDIF"
+ *
+ *----------------------------- Stream 0, playback ----------------------------
+ *
+ * /local/domain/1/device/vsnd/0/2/0/type = "p"
+ * /local/domain/1/device/vsnd/0/2/0/unique-id = "3"
+ *
+ * /local/domain/1/device/vsnd/0/2/0/ring-ref = "389"
+ * /local/domain/1/device/vsnd/0/2/0/event-channel = "152"
+ *
+ ******************************************************************************
+ *                            Backend XenBus Nodes
+ ******************************************************************************
+ *
+ *----------------------------- Protocol version ------------------------------
+ *
+ * versions
+ *      Values:         <string>
+ *
+ *      List of XENSND_LIST_SEPARATOR separated protocol versions supported
+ *      by the backend. For example "1,2,3".
+ *
+ ******************************************************************************
+ *                            Frontend XenBus Nodes
+ ******************************************************************************
+ *
+ *-------------------------------- Addressing ---------------------------------
+ *
+ * dom-id
+ *      Values:         <uint16_t>
+ *
+ *      Domain identifier.
+ *
+ * dev-id
+ *      Values:         <uint16_t>
+ *
+ *      Device identifier.
+ *
+ * pcm-dev-idx
+ *      Values:         <uint8_t>
+ *
+ *      Zero based contigous index of the PCM device.
+ *
+ * stream-idx
+ *      Values:         <uint8_t>
+ *
+ *      Zero based contigous index of the stream of the PCM device.
+ *
+ * The following pattern is used for addressing:
+ *   /local/domain/<dom-id>/device/vsnd/<dev-id>/<pcm-dev-idx>/<stream-idx>/...
+ *
+ *----------------------------- Protocol version ------------------------------
+ *
+ * version
+ *      Values:         <string>
+ *
+ *      Protocol version, chosen among the ones supported by the backend.
+ *
+ *------------------------------- PCM settings --------------------------------
+ *
+ * Every virtualized sound frontend has a set of PCM devices and streams, each
+ * could be individually configured. Part of the PCM configuration can be
+ * defined at higher level of the hierarchy and be fully or partially re-used
+ * by the underlying layers. These configuration values are:
+ *  o number of channels (min/max)
+ *  o supported sample rates
+ *  o supported sample formats.
+ * E.g. one can define these values for the whole card, device or stream.
+ * Every underlying layer in turn can re-define some or all of them to better
+ * fit its needs. For example, card may define number of channels to be
+ * in [1; 8] range, and some particular stream may be limited to [1; 2] only.
+ * The rule is that the underlying layer must be a subset of the upper layer
+ * range.
+ *
+ * channels-min
+ *      Values:         <uint8_t>
+ *
+ *      The minimum amount of channels that is supported, [1; channels-max].
+ *      Optional, if not set or omitted a value of 1 is used.
+ *
+ * channels-max
+ *      Values:         <uint8_t>
+ *
+ *      The maximum amount of channels that is supported.
+ *      Must be at least <channels-min>.
+ *
+ * sample-rates
+ *      Values:         <list of uint32_t>
+ *
+ *      List of supported sample rates separated by XENSND_LIST_SEPARATOR.
+ *      Sample rates are expressed as a list of decimal values w/o any
+ *      ordering requirement.
+ *
+ * sample-formats
+ *      Values:         <list of XENSND_PCM_FORMAT_XXX_STR>
+ *
+ *      List of supported sample formats separated by XENSND_LIST_SEPARATOR.
+ *      Items must not exceed XENSND_SAMPLE_FORMAT_MAX_LEN length.
+ *
+ * buffer-size
+ *      Values:         <uint32_t>
+ *
+ *      The maximum size in octets of the buffer to allocate per stream.
+ *
+ *----------------------- Virtual sound card settings -------------------------
+ * short-name
+ *      Values:         <char[32]>
+ *
+ *      Short name of the virtual sound card. Optional.
+ *
+ * long-name
+ *      Values:         <char[80]>
+ *
+ *      Long name of the virtual sound card. Optional.
+ *
+ *----------------------------- Device settings -------------------------------
+ * name
+ *      Values:         <char[80]>
+ *
+ *      Name of the sound device within the virtual sound card. Optional.
+ *
+ *----------------------------- Stream settings -------------------------------
+ *
+ * type
+ *      Values:         "p", "c"
+ *
+ *      Stream type: "p" - playback stream, "c" - capture stream
+ *
+ *      If both capture and playback are needed then two streams need to be
+ *      defined under the same device.
+ *
+ * unique-id
+ *      Values:         <uint32_t>
+ *
+ *      After stream initialization it is assigned a unique ID (within the front
+ *      driver), so every stream of the frontend can be identified by the
+ *      backend by this ID. This is not equal to stream-idx as the later is
+ *      zero based within the device, but this index is contigous within the
+ *      driver.
+ *
+ *-------------------- Stream Request Transport Parameters --------------------
+ *
+ * event-channel
+ *      Values:         <uint32_t>
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * ring-ref
+ *      Values:         <uint32_t>
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      a sole page in a single page sized ring buffer.
+ *
+ ******************************************************************************
+ *                               STATE DIAGRAMS
+ ******************************************************************************
+ *
+ * Tool stack creates front and back state nodes with initial state
+ * XenbusStateInitialising.
+ * Tool stack creates and sets up frontend sound configuration nodes per domain.
+ *
+ * Front                                Back
+ * =================================    =====================================
+ * XenbusStateInitialising              XenbusStateInitialising
+ *                                       o Query backend device identification
+ *                                         data.
+ *                                       o Open and validate backend device.
+ *                                                      |
+ *                                                      |
+ *                                                      V
+ *                                      XenbusStateInitWait
+ *
+ * o Query frontend configuration
+ * o Allocate and initialize
+ *   event channels per configured
+ *   playback/capture stream.
+ * o Publish transport parameters
+ *   that will be in effect during
+ *   this connection.
+ *              |
+ *              |
+ *              V
+ * XenbusStateInitialised
+ *
+ *                                       o Query frontend transport parameters.
+ *                                       o Connect to the event channels.
+ *                                                      |
+ *                                                      |
+ *                                                      V
+ *                                      XenbusStateConnected
+ *
+ *  o Create and initialize OS
+ *    virtual sound device instances
+ *    as per configuration.
+ *              |
+ *              |
+ *              V
+ * XenbusStateConnected
+ *
+ *                                      XenbusStateUnknown
+ *                                      XenbusStateClosed
+ *                                      XenbusStateClosing
+ * o Remove virtual sound device
+ * o Remove event channels
+ *              |
+ *              |
+ *              V
+ * XenbusStateClosed
+ *
+ *------------------------------- Recovery flow -------------------------------
+ *
+ * In case of frontend unrecoverable errors backend handles that as
+ * if frontend goes into the XenbusStateClosed state.
+ *
+ * In case of backend unrecoverable errors frontend tries removing
+ * the virtualized device. If this is possible at the moment of error,
+ * then frontend goes into the XenbusStateInitialising state and is ready for
+ * new connection with backend. If the virtualized device is still in use and
+ * cannot be removed, then frontend goes into the XenbusStateReconfiguring state
+ * until either the virtualized device removed or backend initiates a new
+ * connection. On the virtualized device removal frontend goes into the
+ * XenbusStateInitialising state.
+ *
+ * Note on XenbusStateReconfiguring state of the frontend: if backend has
+ * unrecoverable errors then frontend cannot send requests to the backend
+ * and thus cannot provide functionality of the virtualized device anymore.
+ * After backend is back to normal the virtualized device may still hold some
+ * state: configuration in use, allocated buffers, client application state etc.
+ * So, in most cases, this will require frontend to implement complex recovery
+ * reconnect logic. Instead, by going into XenbusStateReconfiguring state,
+ * frontend will make sure no new clients of the virtualized device are
+ * accepted, allow existing client(s) to exit gracefully by signaling error
+ * state etc.
+ * Once all the clients are gone frontend can reinitialize the virtualized
+ * device and get into XenbusStateInitialising state again signaling the
+ * backend that a new connection can be made.
+ *
+ * There are multiple conditions possible under which frontend will go from
+ * XenbusStateReconfiguring into XenbusStateInitialising, some of them are OS
+ * specific. For example:
+ * 1. The underlying OS framework may provide callbacks to signal that the last
+ *    client of the virtualized device has gone and the device can be removed
+ * 2. Frontend can schedule a deferred work (timer/tasklet/workqueue)
+ *    to periodically check if this is the right time to re-try removal of
+ *    the virtualized device.
+ * 3. By any other means.
+ *
+ ******************************************************************************
+ *                             PCM FORMATS
+ ******************************************************************************
+ *
+ * XENSND_PCM_FORMAT_<format>[_<endian>]
+ *
+ * format: <S/U/F><bits> or <name>
+ *     S - signed, U - unsigned, F - float
+ *     bits - 8, 16, 24, 32
+ *     name - MU_LAW, GSM, etc.
+ *
+ * endian: <LE/BE>, may be absent
+ *     LE - Little endian, BE - Big endian
+ */
+#define XENSND_PCM_FORMAT_S8		0
+#define XENSND_PCM_FORMAT_U8		1
+#define XENSND_PCM_FORMAT_S16_LE	2
+#define XENSND_PCM_FORMAT_S16_BE	3
+#define XENSND_PCM_FORMAT_U16_LE	4
+#define XENSND_PCM_FORMAT_U16_BE	5
+#define XENSND_PCM_FORMAT_S24_LE	6
+#define XENSND_PCM_FORMAT_S24_BE	7
+#define XENSND_PCM_FORMAT_U24_LE	8
+#define XENSND_PCM_FORMAT_U24_BE	9
+#define XENSND_PCM_FORMAT_S32_LE	10
+#define XENSND_PCM_FORMAT_S32_BE	11
+#define XENSND_PCM_FORMAT_U32_LE	12
+#define XENSND_PCM_FORMAT_U32_BE	13
+#define XENSND_PCM_FORMAT_F32_LE	14 /* 4-byte float, IEEE-754 32-bit, */
+#define XENSND_PCM_FORMAT_F32_BE	15 /* range -1.0 to 1.0              */
+#define XENSND_PCM_FORMAT_F64_LE	16 /* 8-byte float, IEEE-754 64-bit, */
+#define XENSND_PCM_FORMAT_F64_BE	17 /* range -1.0 to 1.0              */
+#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE 18
+#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE 19
+#define XENSND_PCM_FORMAT_MU_LAW	20
+#define XENSND_PCM_FORMAT_A_LAW		21
+#define XENSND_PCM_FORMAT_IMA_ADPCM	22
+#define XENSND_PCM_FORMAT_MPEG		23
+#define XENSND_PCM_FORMAT_GSM		24
+
+/*
+ ******************************************************************************
+ *                             REQUEST CODES
+ ******************************************************************************
+ */
+#define XENSND_OP_OPEN			0
+#define XENSND_OP_CLOSE			1
+#define XENSND_OP_READ			2
+#define XENSND_OP_WRITE			3
+#define XENSND_OP_SET_VOLUME		4
+#define XENSND_OP_GET_VOLUME		5
+#define XENSND_OP_MUTE			6
+#define XENSND_OP_UNMUTE		7
+
+/*
+ ******************************************************************************
+ *               XENSTORE FIELD AND PATH NAME STRINGS, HELPERS
+ ******************************************************************************
+ */
+#define XENSND_DRIVER_NAME		"vsnd"
+
+#define XENSND_LIST_SEPARATOR		","
+/* Field names */
+#define XENSND_FIELD_BE_VERSIONS	"versions"
+#define XENSND_FIELD_FE_VERSION		"version"
+#define XENSND_FIELD_VCARD_SHORT_NAME	"short-name"
+#define XENSND_FIELD_VCARD_LONG_NAME	"long-name"
+#define XENSND_FIELD_RING_REF		"ring-ref"
+#define XENSND_FIELD_EVT_CHNL		"event-channel"
+#define XENSND_FIELD_DEVICE_NAME	"name"
+#define XENSND_FIELD_TYPE		"type"
+#define XENSND_FIELD_STREAM_UNIQUE_ID	"unique-id"
+#define XENSND_FIELD_CHANNELS_MIN	"channels-min"
+#define XENSND_FIELD_CHANNELS_MAX	"channels-max"
+#define XENSND_FIELD_SAMPLE_RATES	"sample-rates"
+#define XENSND_FIELD_SAMPLE_FORMATS	"sample-formats"
+#define XENSND_FIELD_BUFFER_SIZE	"buffer-size"
+
+/* Stream type field values. */
+#define XENSND_STREAM_TYPE_PLAYBACK	"p"
+#define XENSND_STREAM_TYPE_CAPTURE	"c"
+/* Sample rate max string length */
+#define XENSND_SAMPLE_RATE_MAX_LEN	11
+/* Sample format field values */
+#define XENSND_SAMPLE_FORMAT_MAX_LEN	24
+
+#define XENSND_PCM_FORMAT_S8_STR	"s8"
+#define XENSND_PCM_FORMAT_U8_STR	"u8"
+#define XENSND_PCM_FORMAT_S16_LE_STR	"s16_le"
+#define XENSND_PCM_FORMAT_S16_BE_STR	"s16_be"
+#define XENSND_PCM_FORMAT_U16_LE_STR	"u16_le"
+#define XENSND_PCM_FORMAT_U16_BE_STR	"u16_be"
+#define XENSND_PCM_FORMAT_S24_LE_STR	"s24_le"
+#define XENSND_PCM_FORMAT_S24_BE_STR	"s24_be"
+#define XENSND_PCM_FORMAT_U24_LE_STR	"u24_le"
+#define XENSND_PCM_FORMAT_U24_BE_STR	"u24_be"
+#define XENSND_PCM_FORMAT_S32_LE_STR	"s32_le"
+#define XENSND_PCM_FORMAT_S32_BE_STR	"s32_be"
+#define XENSND_PCM_FORMAT_U32_LE_STR	"u32_le"
+#define XENSND_PCM_FORMAT_U32_BE_STR	"u32_be"
+#define XENSND_PCM_FORMAT_F32_LE_STR	"float_le"
+#define XENSND_PCM_FORMAT_F32_BE_STR	"float_be"
+#define XENSND_PCM_FORMAT_F64_LE_STR	"float64_le"
+#define XENSND_PCM_FORMAT_F64_BE_STR	"float64_be"
+#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE_STR "iec958_subframe_le"
+#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE_STR "iec958_subframe_be"
+#define XENSND_PCM_FORMAT_MU_LAW_STR	"mu_law"
+#define XENSND_PCM_FORMAT_A_LAW_STR	"a_law"
+#define XENSND_PCM_FORMAT_IMA_ADPCM_STR	"ima_adpcm"
+#define XENSND_PCM_FORMAT_MPEG_STR	"mpeg"
+#define XENSND_PCM_FORMAT_GSM_STR	"gsm"
+
+
+/*
+ ******************************************************************************
+ *                          STATUS RETURN CODES
+ ******************************************************************************
+ *
+ * Status return code is zero on success and -XEN_EXX on failure.
+ *
+ ******************************************************************************
+ *                              Assumptions
+ ******************************************************************************
+ * o usage of grant reference 0 as invalid grant reference:
+ *   grant reference 0 is valid, but never exposed to a PV driver,
+ *   because of the fact it is already in use/reserved by the PV console.
+ * o all references in this document to page sizes must be treated
+ *   as pages of size XEN_PAGE_SIZE unless otherwise noted.
+ *
+ ******************************************************************************
+ *       Description of the protocol between frontend and backend driver
+ ******************************************************************************
+ *
+ * The two halves of a Para-virtual sound driver communicate with
+ * each other using shared pages and event channels.
+ * Shared page contains a ring with request/response packets.
+ *
+ * Packets, used for input/output operations, e.g. read/write, set/get volume,
+ * etc., provide offset/length fields in order to allow asynchronous protocol
+ * operation with buffer space sharing: part of the buffer allocated at
+ * XENSND_OP_OPEN can be used for audio samples and part, for example,
+ * for volume control.
+ *
+ * All reserved fields in the structures below must be 0.
+ *
+ *---------------------------------- Requests ---------------------------------
+ *
+ * All request packets have the same length (32 octets)
+ * All request packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |    operation   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ *   id - uint16_t, private guest value, echoed in response
+ *   operation - uint8_t, operation code, XENSND_OP_???
+ *
+ * For all packets which use offset and length:
+ *   offset - uint32_t, read or write data offset within the shared buffer,
+ *     passed with XENSND_OP_OPEN request, octets,
+ *     [0; XENSND_OP_OPEN.buffer_sz - 1].
+ *   length - uint32_t, read or write data length, octets
+ *
+ * Request open - open a PCM stream for playback or capture:
+ *
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                | XENSND_OP_OPEN |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                             pcm_rate                              | 12
+ * +----------------+----------------+----------------+----------------+
+ * |  pcm_format    |  pcm_channels  |             reserved            | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             buffer_sz                             | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                           gref_directory                          | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 28
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * pcm_rate - uint32_t, stream data rate, Hz
+ * pcm_format - uint8_t, XENSND_PCM_FORMAT_XXX value
+ * pcm_channels - uint8_t, number of channels of this stream,
+ *   [channels-min; channels-max]
+ * buffer_sz - uint32_t, buffer size to be allocated, octets
+ * gref_directory - grant_ref_t, a reference to the first shared page
+ *   describing shared buffer references. At least one page exists. If shared
+ *   buffer size  (buffer_sz) exceeds what can be addressed by this single page,
+ *   then reference to the next page must be supplied (see gref_dir_next_page
+ *   below)
+ */
+
+struct xensnd_open_req {
+	uint32_t pcm_rate;
+	uint8_t pcm_format;
+	uint8_t pcm_channels;
+	uint16_t reserved;
+	uint32_t buffer_sz;
+	grant_ref_t gref_directory;
+};
+
+/*
+ * Shared page for XENSND_OP_OPEN buffer descriptor (gref_directory in the
+ *   request) employs a list of pages, describing all pages of the shared data
+ *   buffer:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |                        gref_dir_next_page                         | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              gref[0]                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                              gref[i]                              | i*4+8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             gref[N - 1]                           | N*4+8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * gref_dir_next_page - grant_ref_t, reference to the next page describing
+ *   page directory. Must be 0 if there are no more pages in the list.
+ * gref[i] - grant_ref_t, reference to a shared page of the buffer
+ *   allocated at XENSND_OP_OPEN
+ *
+ * Number of grant_ref_t entries in the whole page directory is not
+ * passed, but instead can be calculated as:
+ *   num_grefs_total = (XENSND_OP_OPEN.buffer_sz + XEN_PAGE_SIZE - 1) /
+ *       XEN_PAGE_SIZE
+ */
+
+struct xensnd_page_directory {
+	grant_ref_t gref_dir_next_page;
+	grant_ref_t gref[1]; /* Variable length */
+};
+
+/*
+ *  Request close - close an opened pcm stream:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                | XENSND_OP_CLOSE|    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Request read/write - used for read (for capture) or write (for playback):
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   operation    |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                              offset                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                              length                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * operation - XENSND_OP_READ for read or XENSND_OP_WRITE for write
+ */
+
+struct xensnd_rw_req {
+	uint32_t offset;
+	uint32_t length;
+};
+
+/*
+ * Request set/get volume - set/get channels' volume of the stream given:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   operation    |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                              offset                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                              length                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * operation - XENSND_OP_SET_VOLUME for volume set
+ *   or XENSND_OP_GET_VOLUME for volume get
+ * Buffer passed with XENSND_OP_OPEN is used to exchange volume
+ * values:
+ *
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |                             channel[0]                            | 4
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             channel[i]                            | i*4
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                           channel[N - 1]                          | (N-1)*4
+ * +----------------+----------------+----------------+----------------+
+ *
+ * N = XENSND_OP_OPEN.pcm_channels
+ * i - uint8_t, index of a channel
+ * channel[i] - sint32_t, volume of i-th channel
+ * Volume is expressed as a signed value in steps of 0.001 dB,
+ * while 0 being 0 dB.
+ *
+ * Request mute/unmute - mute/unmute stream:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   operation    |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                              offset                               | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                              length                               | 16
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * operation - XENSND_OP_MUTE for mute or XENSND_OP_UNMUTE for unmute
+ * Buffer passed with XENSND_OP_OPEN is used to exchange mute/unmute
+ * values:
+ *
+ *                                   0                                 octet
+ * +----------------+----------------+----------------+----------------+
+ * |                             channel[0]                            | 4
+ * +----------------+----------------+----------------+----------------+
+ * +/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             channel[i]                            | i*4
+ * +----------------+----------------+----------------+----------------+
+ * +/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                           channel[N - 1]                          | (N-1)*4
+ * +----------------+----------------+----------------+----------------+
+ *
+ * N = XENSND_OP_OPEN.pcm_channels
+ * i - uint8_t, index of a channel
+ * channel[i] - uint8_t, non-zero if i-th channel needs to be muted/unmuted
+ *
+ *------------------------------------ N.B. -----------------------------------
+ *
+ * The 'struct xensnd_rw_req' is also used for XENSND_OP_SET_VOLUME,
+ * XENSND_OP_GET_VOLUME, XENSND_OP_MUTE, XENSND_OP_UNMUTE.
+ */
+
+/*
+ *---------------------------------- Responses --------------------------------
+ *
+ * All response packets have the same length (32 octets)
+ *
+ * Response for all requests:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |    operation   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              status                               | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 12
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
+ * +----------------+----------------+----------------+----------------+
+ *
+ * id - uint16_t, copied from the request
+ * operation - uint8_t, XENSND_OP_* - copied from request
+ * status - int32_t, response status, zero on success and -XEN_EXX on failure
+ */
+
+struct xensnd_req {
+	uint16_t id;
+	uint8_t operation;
+	uint8_t reserved[5];
+	union {
+		struct xensnd_open_req open;
+		struct xensnd_rw_req rw;
+		uint8_t reserved[24];
+	} op;
+};
+
+struct xensnd_resp {
+	uint16_t id;
+	uint8_t operation;
+	uint8_t reserved;
+	int32_t status;
+	uint8_t reserved1[24];
+};
+
+DEFINE_RING_TYPES(xen_sndif, struct xensnd_req, struct xensnd_resp);
+
+#endif /* __XEN_PUBLIC_IO_SNDIF_H__ */

include/xen/xen-ops.h

···
 void xen_arch_resume(void);
 void xen_arch_suspend(void);
 
+void xen_reboot(int reason);
+
 void xen_resume_notifier_register(struct notifier_block *nb);
 void xen_resume_notifier_unregister(struct notifier_block *nb);
 
···
 int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
+
+#ifdef CONFIG_XEN_PV
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				unsigned int address_bits,
 				dma_addr_t *dma_handle);
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
+#else
+static inline int xen_create_contiguous_region(phys_addr_t pstart,
+					       unsigned int order,
+					       unsigned int address_bits,
+					       dma_addr_t *dma_handle)
+{
+	return 0;
+}
+
+static inline void xen_destroy_contiguous_region(phys_addr_t pstart,
+						 unsigned int order) { }
+#endif
 
 struct vm_area_struct;
 
···
 efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 					unsigned long count, u64 *max_size,
 					int *reset_type);
+void xen_efi_reset_system(int reset_type, efi_status_t status,
+			  unsigned long data_size, efi_char16_t *data);
+
 
 #ifdef CONFIG_PREEMPT
 

net/9p/Kconfig

···
 	  This builds support for a transports between
 	  guest partitions and a host partition.
 
+config NET_9P_XEN
+	depends on XEN
+	select XEN_XENBUS_FRONTEND
+	tristate "9P Xen Transport"
+	help
+	  This builds support for a transport for 9pfs between
+	  two Xen domains.
+
+
 config NET_9P_RDMA
 	depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS
 	tristate "9P RDMA Transport (Experimental)"

net/9p/Makefile

···
 obj-$(CONFIG_NET_9P) := 9pnet.o
+obj-$(CONFIG_NET_9P_XEN) += 9pnet_xen.o
 obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
 obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 
···
 
 9pnet_virtio-objs := \
 	trans_virtio.o \
+
+9pnet_xen-objs := \
+	trans_xen.o \
 
 9pnet_rdma-objs := \
 	trans_rdma.o \

net/9p/trans_xen.c

···
+/*
+ * linux/fs/9p/trans_xen
+ *
+ * Xen transport layer.
+ *
+ * Copyright (C) 2017 by Stefano Stabellini <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/9pfs.h>
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/rwlock.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+
+#define XEN_9PFS_NUM_RINGS 2
+#define XEN_9PFS_RING_ORDER 6
+#define XEN_9PFS_RING_SIZE  XEN_FLEX_RING_SIZE(XEN_9PFS_RING_ORDER)
+
+struct xen_9pfs_header {
+	uint32_t size;
+	uint8_t id;
+	uint16_t tag;
+
+	/* uint8_t sdata[]; */
+} __attribute__((packed));
+
+/* One per ring, more than one per 9pfs share */
+struct xen_9pfs_dataring {
+	struct xen_9pfs_front_priv *priv;
+
+	struct xen_9pfs_data_intf *intf;
+	grant_ref_t ref;
+	int evtchn;
+	int irq;
+	/* protect a ring from concurrent accesses */
+	spinlock_t lock;
+
+	struct xen_9pfs_data data;
+	wait_queue_head_t wq;
+	struct work_struct work;
+};
+
+/* One per 9pfs share */
+struct xen_9pfs_front_priv {
+	struct list_head list;
+	struct xenbus_device *dev;
+	char *tag;
+	struct p9_client *client;
+
+	int num_rings;
+	struct xen_9pfs_dataring *rings;
+};
+
+static LIST_HEAD(xen_9pfs_devs);
+static DEFINE_RWLOCK(xen_9pfs_lock);
+
+/* We don't currently allow canceling of requests */
+static int p9_xen_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+static int p9_xen_create(struct p9_client *client, const char *addr, char *args)
+{
+	struct xen_9pfs_front_priv *priv;
+
+	read_lock(&xen_9pfs_lock);
+	list_for_each_entry(priv, &xen_9pfs_devs, list) {
+		if (!strcmp(priv->tag, addr)) {
+			priv->client = client;
+			read_unlock(&xen_9pfs_lock);
+			return 0;
+		}
+	}
+	read_unlock(&xen_9pfs_lock);
+	return -EINVAL;
+}
+
+static void p9_xen_close(struct p9_client *client)
+{
+	struct xen_9pfs_front_priv *priv;
+
+	read_lock(&xen_9pfs_lock);
+	list_for_each_entry(priv, &xen_9pfs_devs, list) {
+		if (priv->client == client) {
+			priv->client = NULL;
+			read_unlock(&xen_9pfs_lock);
+			return;
+		}
+	}
+	read_unlock(&xen_9pfs_lock);
+}
+
+static bool p9_xen_write_todo(struct xen_9pfs_dataring *ring, RING_IDX size)
+{
+	RING_IDX cons, prod;
+
+	cons = ring->intf->out_cons;
+	prod = ring->intf->out_prod;
+	virt_mb();
+
+	return XEN_9PFS_RING_SIZE -
+		xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE) >= size;
+}
+
+static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
+{
+	struct xen_9pfs_front_priv *priv = NULL;
+	RING_IDX cons, prod, masked_cons, masked_prod;
+	unsigned long flags;
+	u32 size = p9_req->tc->size;
+	struct xen_9pfs_dataring *ring;
+	int num;
+
+	read_lock(&xen_9pfs_lock);
+	list_for_each_entry(priv, &xen_9pfs_devs, list) {
+		if (priv->client == client)
+			break;
+	}
+	read_unlock(&xen_9pfs_lock);
+	if (!priv || priv->client != client)
+		return -EINVAL;
+
+	num = p9_req->tc->tag % priv->num_rings;
+	ring = &priv->rings[num];
+
+again:
+	while (wait_event_interruptible(ring->wq,
+					p9_xen_write_todo(ring, size)) != 0)
+		;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	cons = ring->intf->out_cons;
+	prod = ring->intf->out_prod;
+	virt_mb();
+
+	if (XEN_9PFS_RING_SIZE - xen_9pfs_queued(prod, cons,
+						 XEN_9PFS_RING_SIZE) < size) {
+		spin_unlock_irqrestore(&ring->lock, flags);
+		goto again;
+	}
+
+	masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE);
+	masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
+
+	xen_9pfs_write_packet(ring->data.out, p9_req->tc->sdata, size,
+			      &masked_prod, masked_cons, XEN_9PFS_RING_SIZE);
+
+	p9_req->status = REQ_STATUS_SENT;
+	virt_wmb();			/* write ring before updating pointer */
+	prod += size;
+	ring->intf->out_prod = prod;
+	spin_unlock_irqrestore(&ring->lock, flags);
+	notify_remote_via_irq(ring->irq);
+
+	return 0;
+}
+
+static void p9_xen_response(struct work_struct *work)
+{
+	struct xen_9pfs_front_priv *priv;
+	struct xen_9pfs_dataring *ring;
+	RING_IDX cons, prod, masked_cons, masked_prod;
+	struct xen_9pfs_header h;
+	struct p9_req_t *req;
+	int status;
+
+	ring = container_of(work, struct xen_9pfs_dataring, work);
+	priv = ring->priv;
+
+	while (1) {
+		cons = ring->intf->in_cons;
+		prod = ring->intf->in_prod;
+		virt_rmb();
+
+		if (xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE) <
+		    sizeof(h)) {
+			notify_remote_via_irq(ring->irq);
+			return;
+		}
+
+		masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE);
+		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
+
+		/* First, read just the header */
+		xen_9pfs_read_packet(&h, ring->data.in, sizeof(h),
+				     masked_prod, &masked_cons,
+				     XEN_9PFS_RING_SIZE);
+
+		req = p9_tag_lookup(priv->client, h.tag);
+		if (!req || req->status != REQ_STATUS_SENT) {
+			dev_warn(&priv->dev->dev, "Wrong req tag=%x\n", h.tag);
+			cons += h.size;
+			virt_mb();
+			ring->intf->in_cons = cons;
+			continue;
+		}
+
+		memcpy(req->rc, &h, sizeof(h));
+		req->rc->offset = 0;
+
+		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
+		/* Then, read the whole packet (including the header) */
+		xen_9pfs_read_packet(req->rc->sdata, ring->data.in, h.size,
+				     masked_prod, &masked_cons,
+				     XEN_9PFS_RING_SIZE);
+
+		virt_mb();
+		cons += h.size;
+		ring->intf->in_cons = cons;
+
+		status = (req->status != REQ_STATUS_ERROR) ?
+			REQ_STATUS_RCVD : REQ_STATUS_ERROR;
+
+		p9_client_cb(priv->client, req, status);
+	}
+}
+
+static irqreturn_t xen_9pfs_front_event_handler(int irq, void *r)
+{
+	struct xen_9pfs_dataring *ring = r;
+
+	if (!ring || !ring->priv->client) {
+		/* ignore spurious interrupt */
+		return IRQ_HANDLED;
+	}
+
+	wake_up_interruptible(&ring->wq);
+	schedule_work(&ring->work);
+
+	return IRQ_HANDLED;
+}
+
+static struct p9_trans_module p9_xen_trans = {
+	.name = "xen",
+	.maxsize = 1 << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT),
+	.def = 1,
+	.create = p9_xen_create,
+	.close = p9_xen_close,
+	.request = p9_xen_request,
+	.cancel = p9_xen_cancel,
+	.owner = THIS_MODULE,
+};
+
+static const struct xenbus_device_id xen_9pfs_front_ids[] = {
+	{ "9pfs" },
+	{ "" }
+};
+
+static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv)
+{
+	int i, j;
+
+	write_lock(&xen_9pfs_lock);
+	list_del(&priv->list);
+	write_unlock(&xen_9pfs_lock);
+
+	for (i = 0; i < priv->num_rings; i++) {
+		if (!priv->rings[i].intf)
+			break;
+		if (priv->rings[i].irq > 0)
+			unbind_from_irqhandler(priv->rings[i].irq, priv->dev);
+		if (priv->rings[i].data.in) {
+			for (j = 0; j < (1 << XEN_9PFS_RING_ORDER); j++) {
+				grant_ref_t ref;
+
+				ref = priv->rings[i].intf->ref[j];
+				gnttab_end_foreign_access(ref, 0, 0);
+			}
+			free_pages((unsigned long)priv->rings[i].data.in,
+				   XEN_9PFS_RING_ORDER -
+				   (PAGE_SHIFT - XEN_PAGE_SHIFT));
+		}
+		gnttab_end_foreign_access(priv->rings[i].ref, 0, 0);
+		free_page((unsigned long)priv->rings[i].intf);
+	}
+	kfree(priv->rings);
+	kfree(priv->tag);
+	kfree(priv);
+}
+
+static int xen_9pfs_front_remove(struct xenbus_device *dev)
+{
+	struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);
+
+	dev_set_drvdata(&dev->dev, NULL);
+	xen_9pfs_front_free(priv);
+	return 0;
+}
+
+static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
+					 struct xen_9pfs_dataring *ring)
+{
+	int i = 0;
+	int ret = -ENOMEM;
+	void *bytes = NULL;
+
+	init_waitqueue_head(&ring->wq);
+	spin_lock_init(&ring->lock);
+	INIT_WORK(&ring->work, p9_xen_response);
+
+	ring->intf = (struct xen_9pfs_data_intf *)get_zeroed_page(GFP_KERNEL);
+	if (!ring->intf)
+		return ret;
+	ret = gnttab_grant_foreign_access(dev->otherend_id,
+					  virt_to_gfn(ring->intf), 0);
+	if (ret < 0)
+		goto out;
+	ring->ref = ret;
+	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+			XEN_9PFS_RING_ORDER - (PAGE_SHIFT - XEN_PAGE_SHIFT));
+	if (!bytes) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (; i < (1 << XEN_9PFS_RING_ORDER); i++) {
+		ret = gnttab_grant_foreign_access(
+				dev->otherend_id, virt_to_gfn(bytes) + i, 0);
+		if (ret < 0)
+			goto out;
+		ring->intf->ref[i] = ret;
+	}
+	ring->intf->ring_order = XEN_9PFS_RING_ORDER;
+	ring->data.in = bytes;
+	ring->data.out = bytes + XEN_9PFS_RING_SIZE;
+
+	ret = xenbus_alloc_evtchn(dev, &ring->evtchn);
+	if (ret)
+		goto out;
+	ring->irq = bind_evtchn_to_irqhandler(ring->evtchn,
+					      xen_9pfs_front_event_handler,
+					      0, "xen_9pfs-frontend", ring);
+	if (ring->irq >= 0)
+		return 0;
+
+	xenbus_free_evtchn(dev, ring->evtchn);
+	ret = ring->irq;
+out:
+	if (bytes) {
+		for (i--; i >= 0; i--)
+			gnttab_end_foreign_access(ring->intf->ref[i], 0, 0);
+		free_pages((unsigned long)bytes,
+			   XEN_9PFS_RING_ORDER -
+			   (PAGE_SHIFT - XEN_PAGE_SHIFT));
+	}
+	gnttab_end_foreign_access(ring->ref, 0, 0);
+	free_page((unsigned long)ring->intf);
+	return ret;
+}
+
+static int xen_9pfs_front_probe(struct xenbus_device *dev,
+				const struct xenbus_device_id *id)
+{
+	int ret, i;
+	struct xenbus_transaction xbt;
+	struct xen_9pfs_front_priv *priv = NULL;
+	char *versions;
+	unsigned int max_rings, max_ring_order, len = 0;
+
+	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
+	if (!len)
+		return -EINVAL;
+	if (strcmp(versions, "1")) {
+		kfree(versions);
+		return -EINVAL;
+	}
+	kfree(versions);
+	max_rings = xenbus_read_unsigned(dev->otherend, "max-rings", 0);
+	if (max_rings < XEN_9PFS_NUM_RINGS)
+		return -EINVAL;
+	max_ring_order = xenbus_read_unsigned(dev->otherend,
+					      "max-ring-page-order", 0);
+	if (max_ring_order < XEN_9PFS_RING_ORDER)
+		return -EINVAL;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->num_rings = XEN_9PFS_NUM_RINGS;
+	priv->rings = kcalloc(priv->num_rings, sizeof(*priv->rings),
+			      GFP_KERNEL);
+	if (!priv->rings) {
+		kfree(priv);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < priv->num_rings; i++) {
+		priv->rings[i].priv = priv;
+		ret = xen_9pfs_front_alloc_dataring(dev, &priv->rings[i]);
+		if (ret < 0)
+			goto error;
+	}
+
+ again:
+	ret = xenbus_transaction_start(&xbt);
+	if (ret) {
+		xenbus_dev_fatal(dev, ret, "starting transaction");
+		goto error;
+	}
+	ret = xenbus_printf(xbt, dev->nodename, "version", "%u", 1);
+	if (ret)
+		goto error_xenbus;
+	ret = xenbus_printf(xbt, dev->nodename, "num-rings", "%u",
+			    priv->num_rings);
+	if (ret)
+		goto error_xenbus;
+	for (i = 0; i < priv->num_rings; i++) {
+		char str[16];
+
+		BUILD_BUG_ON(XEN_9PFS_NUM_RINGS > 9);
+		sprintf(str, "ring-ref%u", i);
+		ret = xenbus_printf(xbt, dev->nodename, str, "%d",
+				    priv->rings[i].ref);
+		if (ret)
+			goto error_xenbus;
+
+		sprintf(str, "event-channel-%u", i);
+		ret = xenbus_printf(xbt, dev->nodename, str, "%u",
+				    priv->rings[i].evtchn);
+		if (ret)
+			goto error_xenbus;
+	}
+	priv->tag = xenbus_read(xbt, dev->nodename, "tag", NULL);
+	if (!priv->tag) {
+		ret = -EINVAL;
+		goto error_xenbus;
+	}
+	ret = xenbus_transaction_end(xbt, 0);
+	if (ret) {
+		if (ret == -EAGAIN)
+			goto again;
+		xenbus_dev_fatal(dev, ret, "completing transaction");
+		goto error;
+	}
+
+	write_lock(&xen_9pfs_lock);
+	list_add_tail(&priv->list, &xen_9pfs_devs);
+	write_unlock(&xen_9pfs_lock);
+	dev_set_drvdata(&dev->dev, priv);
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+ error_xenbus:
+	xenbus_transaction_end(xbt, 1);
+	xenbus_dev_fatal(dev, ret, "writing xenstore");
+ error:
+	dev_set_drvdata(&dev->dev, NULL);
+	xen_9pfs_front_free(priv);
+	return ret;
+}
+
+static int xen_9pfs_front_resume(struct xenbus_device *dev)
+{
+	dev_warn(&dev->dev, "suspsend/resume unsupported\n");
+	return 0;
+}
+
+static void xen_9pfs_front_changed(struct xenbus_device *dev,
+				   enum xenbus_state backend_state)
+{
+	switch (backend_state) {
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
+	case XenbusStateInitialising:
+	case XenbusStateInitialised:
+	case XenbusStateUnknown:
+		break;
+
+	case XenbusStateInitWait:
+		break;
+
+	case XenbusStateConnected:
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's CLOSING state -- fallthrough */
+	case XenbusStateClosing:
+		xenbus_frontend_closed(dev);
+		break;
+	}
+}
+
+static struct xenbus_driver xen_9pfs_front_driver = {
+	.ids = xen_9pfs_front_ids,
+	.probe = xen_9pfs_front_probe,
+	.remove = xen_9pfs_front_remove,
+	.resume = xen_9pfs_front_resume,
+	.otherend_changed = xen_9pfs_front_changed,
+};
+
+int p9_trans_xen_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	pr_info("Initialising Xen transport for 9pfs\n");
+
+	v9fs_register_trans(&p9_xen_trans);
+	return xenbus_register_frontend(&xen_9pfs_front_driver);
+}
+module_init(p9_trans_xen_init);
+
+void p9_trans_xen_exit(void)
+{
+	v9fs_unregister_trans(&p9_xen_trans);
+	return xenbus_unregister_driver(&xen_9pfs_front_driver);
+}
+module_exit(p9_trans_xen_exit);