Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (249 commits)
  KVM: Move apic timer migration away from critical section
  KVM: Put kvm_para.h include outside __KERNEL__
  KVM: Fix unbounded preemption latency
  KVM: Initialize the mmu caches only after verifying cpu support
  KVM: MMU: Fix dirty page setting for pages removed from rmap
  KVM: Portability: Move kvm_fpu to asm-x86/kvm.h
  KVM: x86 emulator: Only allow VMCALL/VMMCALL trapped by #UD
  KVM: MMU: Merge shadow level check in FNAME(fetch)
  KVM: MMU: Move kvm_free_some_pages() into critical section
  KVM: MMU: Switch to mmu spinlock
  KVM: MMU: Avoid calling gfn_to_page() in mmu_set_spte()
  KVM: Add kvm_read_guest_atomic()
  KVM: MMU: Concurrent guest walkers
  KVM: Disable vapic support on Intel machines with FlexPriority
  KVM: Accelerated apic support
  KVM: local APIC TPR access reporting facility
  KVM: Print data for unimplemented wrmsr
  KVM: MMU: Add cache miss statistic
  KVM: MMU: Coalesce remote tlb flushes
  KVM: Expose ioapic to ia64 save/restore APIs
  ...

arch/x86/Kconfig

@@ -107,6 +107,7 @@ config ARCH_SUPPORTS_OPROFILE
 	bool
 	default y
 
+select HAVE_KVM
 
 config ZONE_DMA32
 	bool
@@ -1598,4 +1599,6 @@ source "security/Kconfig"
 
 source "crypto/Kconfig"
 
+source "arch/x86/kvm/Kconfig"
+
 source "lib/Kconfig"

arch/x86/Makefile

@@ -7,6 +7,8 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
+core-$(CONFIG_KVM) += arch/x86/kvm/
+
 # BITS is used as extension for files which are available in a 32 bit
 # and a 64 bit version to simplify shared Makefiles.
 # e.g.: obj-y += foo_$(BITS).o

drivers/kvm/Kconfig → arch/x86/kvm/Kconfig

 #
 # KVM configuration
 #
+config HAVE_KVM
+       bool
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
-	depends on X86
+	depends on HAVE_KVM || X86
 	default y
 	---help---
 	  Say Y here to get to see options for using your Linux host to run other
@@ -16,7 +19,7 @@ if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
-	depends on X86 && EXPERIMENTAL
+	depends on HAVE_KVM && EXPERIMENTAL
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	---help---

drivers/kvm/Makefile → arch/x86/kvm/Makefile

@@ -2,7 +2,11 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-kvm-objs := kvm_main.o mmu.o x86_emulate.o i8259.o irq.o lapic.o ioapic.o
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
+
+kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o
 obj-$(CONFIG_KVM) += kvm.o
 kvm-intel-objs = vmx.o
 obj-$(CONFIG_KVM_INTEL) += kvm-intel.o

drivers/kvm/i8259.c → arch/x86/kvm/i8259.c

@@ -28,6 +28,8 @@
 #include <linux/mm.h>
 #include "irq.h"
 
+#include <linux/kvm_host.h>
+
 /*
  * set irq level. If an edge is detected, then the IRR is set to 1
  */
@@ -181,10 +183,8 @@ int kvm_pic_read_irq(struct kvm_pic *s)
 	return intno;
 }
 
-static void pic_reset(void *opaque)
+void kvm_pic_reset(struct kvm_kpic_state *s)
 {
-	struct kvm_kpic_state *s = opaque;
-
 	s->last_irr = 0;
 	s->irr = 0;
 	s->imr = 0;
@@ -209,7 +209,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 	addr &= 1;
 	if (addr == 0) {
 		if (val & 0x10) {
-			pic_reset(s);	/* init */
+			kvm_pic_reset(s);	/* init */
 			/*
 			 * deassert a pending interrupt
 			 */

drivers/kvm/irq.c → arch/x86/kvm/irq.c

@@ -20,8 +20,8 @@
  */
 
 #include <linux/module.h>
+#include <linux/kvm_host.h>
 
-#include "kvm.h"
 #include "irq.h"
 
 /*
@@ -63,26 +63,6 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 }
 EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
-static void vcpu_kick_intr(void *info)
-{
-#ifdef DEBUG
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
-	printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu);
-#endif
-}
-
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
-{
-	int ipi_pcpu = vcpu->cpu;
-
-	if (waitqueue_active(&vcpu->wq)) {
-		wake_up_interruptible(&vcpu->wq);
-		++vcpu->stat.halt_wakeup;
-	}
-	if (vcpu->guest_mode)
-		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
-}
-
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_apic_timer_irqs(vcpu);

drivers/kvm/irq.h → arch/x86/kvm/irq.h

@@ -22,7 +22,16 @@
 #ifndef __IRQ_H
 #define __IRQ_H
 
-#include "kvm.h"
+#include <linux/mm_types.h>
+#include <linux/hrtimer.h>
+#include <linux/kvm_host.h>
+
+#include "iodev.h"
+#include "ioapic.h"
+#include "lapic.h"
+
+struct kvm;
+struct kvm_vcpu;
 
 typedef void irq_request_func(void *opaque, int level);
 
@@ -57,109 +66,23 @@ struct kvm_pic {
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
 void kvm_pic_set_irq(void *opaque, int irq, int level);
 int kvm_pic_read_irq(struct kvm_pic *s);
-int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
 void kvm_pic_update_irq(struct kvm_pic *s);
 
-#define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
-#define IOAPIC_VERSION_ID 0x11	/* IOAPIC version */
-#define IOAPIC_EDGE_TRIG  0
-#define IOAPIC_LEVEL_TRIG 1
-
-#define IOAPIC_DEFAULT_BASE_ADDRESS  0xfec00000
-#define IOAPIC_MEM_LENGTH            0x100
+static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
+{
+	return kvm->arch.vpic;
+}
 
-/* Direct registers. */
-#define IOAPIC_REG_SELECT  0x00
-#define IOAPIC_REG_WINDOW  0x10
-#define IOAPIC_REG_EOI     0x40	/* IA64 IOSAPIC only */
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+	return pic_irqchip(kvm) != NULL;
+}
 
-/* Indirect registers. */
-#define IOAPIC_REG_APIC_ID 0x00	/* x86 IOAPIC only */
-#define IOAPIC_REG_VERSION 0x01
-#define IOAPIC_REG_ARB_ID  0x02	/* x86 IOAPIC only */
-
-struct kvm_ioapic {
-	u64 base_address;
-	u32 ioregsel;
-	u32 id;
-	u32 irr;
-	u32 pad;
-	union ioapic_redir_entry {
-		u64 bits;
-		struct {
-			u8 vector;
-			u8 delivery_mode:3;
-			u8 dest_mode:1;
-			u8 delivery_status:1;
-			u8 polarity:1;
-			u8 remote_irr:1;
-			u8 trig_mode:1;
-			u8 mask:1;
-			u8 reserve:7;
-			u8 reserved[4];
-			u8 dest_id;
-		} fields;
-	} redirtbl[IOAPIC_NUM_PINS];
-	struct kvm_io_device dev;
-	struct kvm *kvm;
-};
-
-struct kvm_lapic {
-	unsigned long base_address;
-	struct kvm_io_device dev;
-	struct {
-		atomic_t pending;
-		s64 period;	/* unit: ns */
-		u32 divide_count;
-		ktime_t last_update;
-		struct hrtimer dev;
-	} timer;
-	struct kvm_vcpu *vcpu;
-	struct page *regs_page;
-	void *regs;
-};
-
-#ifdef DEBUG
-#define ASSERT(x)  							\
-do {									\
-	if (!(x)) {							\
-		printk(KERN_EMERG "assertion failed %s: %d: %s\n",	\
-		       __FILE__, __LINE__, #x);				\
-		BUG();							\
-	}								\
-} while (0)
-#else
-#define ASSERT(x) do { } while (0)
-#endif
+void kvm_pic_reset(struct kvm_kpic_state *s);
 
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
-int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
-int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
-int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
-void kvm_lapic_reset(struct kvm_vcpu *vcpu);
-void kvm_free_apic(struct kvm_lapic *apic);
-u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
-void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
-void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
-struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap);
-u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
-void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
-int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
-void kvm_ioapic_update_eoi(struct kvm *kvm, int vector);
-int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
-int kvm_apic_set_irq(struct kvm_lapic *apic, u8 vec, u8 trig);
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
-int kvm_ioapic_init(struct kvm *kvm);
-void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
-int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
-void kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
+void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
 
 #endif

drivers/kvm/kvm_svm.h → arch/x86/kvm/kvm_svm.h

@@ -4,10 +4,10 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/list.h>
+#include <linux/kvm_host.h>
 #include <asm/msr.h>
 
 #include "svm.h"
-#include "kvm.h"
 
 static const u32 host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64

arch/x86/kvm/lapic.h

+#ifndef __KVM_X86_LAPIC_H
+#define __KVM_X86_LAPIC_H
+
+#include "iodev.h"
+
+#include <linux/kvm_host.h>
+
+struct kvm_lapic {
+	unsigned long base_address;
+	struct kvm_io_device dev;
+	struct {
+		atomic_t pending;
+		s64 period;	/* unit: ns */
+		u32 divide_count;
+		ktime_t last_update;
+		struct hrtimer dev;
+	} timer;
+	struct kvm_vcpu *vcpu;
+	struct page *regs_page;
+	void *regs;
+	gpa_t vapic_addr;
+	struct page *vapic_page;
+};
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
+void kvm_free_lapic(struct kvm_vcpu *vcpu);
+
+int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
+int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
+void kvm_lapic_reset(struct kvm_vcpu *vcpu);
+u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
+void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
+void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+
+u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
+void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
+int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
+int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
+void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
+
+void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
+void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
+
+#endif

arch/x86/kvm/mmu.h

+#ifndef __KVM_X86_MMU_H
+#define __KVM_X86_MMU_H
+
+#include <linux/kvm_host.h>
+
+static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
+		__kvm_mmu_free_some_pages(vcpu);
+}
+
+static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
+{
+	if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
+		return 0;
+
+	return kvm_mmu_load(vcpu);
+}
+
+static inline int is_long_mode(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_X86_64
+	return vcpu->arch.shadow_efer & EFER_LME;
+#else
+	return 0;
+#endif
+}
+
+static inline int is_pae(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr4 & X86_CR4_PAE;
+}
+
+static inline int is_pse(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr4 & X86_CR4_PSE;
+}
+
+static inline int is_paging(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr0 & X86_CR0_PG;
+}
+
+#endif

drivers/kvm/segment_descriptor.h → arch/x86/kvm/segment_descriptor.h

+#ifndef __SEGMENT_DESCRIPTOR_H
+#define __SEGMENT_DESCRIPTOR_H
+
 struct segment_descriptor {
 	u16 limit_low;
 	u16 base_low;
@@ -14,4 +17,13 @@ struct segment_descriptor {
 	u8  base_high;
 } __attribute__((packed));
 
+#ifdef CONFIG_X86_64
+/* LDT or TSS descriptor in the GDT. 16 bytes. */
+struct segment_descriptor_64 {
+	struct segment_descriptor s;
+	u32 base_higher;
+	u32 pad_zero;
+};
 
+#endif
+#endif

drivers/kvm/svm.h → arch/x86/kvm/svm.h

@@ -204,6 +204,7 @@ struct __attribute__ ((__packed__)) vmcb {
 #define INTERCEPT_CR0_MASK 1
 #define INTERCEPT_CR3_MASK (1 << 3)
 #define INTERCEPT_CR4_MASK (1 << 4)
+#define INTERCEPT_CR8_MASK (1 << 8)
 
 #define INTERCEPT_DR0_MASK 1
 #define INTERCEPT_DR1_MASK (1 << 1)
@@ -311,7 +312,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXIT_ERR		-1
 
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) // TS and MP
+#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
 
 #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
 #define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"

drivers/kvm/vmx.h → arch/x86/kvm/vmx.h

@@ -25,6 +25,9 @@
  *
  */
 
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
 #define CPU_BASED_VIRTUAL_INTR_PENDING          0x00000004
 #define CPU_BASED_USE_TSC_OFFSETING             0x00000008
 #define CPU_BASED_HLT_EXITING                   0x00000080
@@ -42,6 +45,12 @@
 #define CPU_BASED_MONITOR_EXITING               0x20000000
 #define CPU_BASED_PAUSE_EXITING                 0x40000000
 #define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS   0x80000000
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
 #define PIN_BASED_NMI_EXITING                   0x00000008
@@ -54,8 +63,6 @@
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
 
-#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
-
 /* VMCS Encodings */
 enum vmcs_field {
 	GUEST_ES_SELECTOR               = 0x00000800,
@@ -89,6 +96,8 @@ enum vmcs_field {
 	TSC_OFFSET_HIGH                 = 0x00002011,
 	VIRTUAL_APIC_PAGE_ADDR          = 0x00002012,
 	VIRTUAL_APIC_PAGE_ADDR_HIGH     = 0x00002013,
+	APIC_ACCESS_ADDR		= 0x00002014,
+	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
 	VMCS_LINK_POINTER               = 0x00002800,
 	VMCS_LINK_POINTER_HIGH          = 0x00002801,
 	GUEST_IA32_DEBUGCTL             = 0x00002802,
@@ -214,6 +223,8 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_WBINVD		54
 
 /*
  * Interruption-information format
@@ -230,13 +241,14 @@ enum vmcs_field {
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
 #define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
+#define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
 
 /*
  * Exit Qualifications for MOV for Control Register Access
  */
-#define CONTROL_REG_ACCESS_NUM          0x7     /* 2:0, number of control register */
+#define CONTROL_REG_ACCESS_NUM          0x7     /* 2:0, number of control reg.*/
 #define CONTROL_REG_ACCESS_TYPE         0x30    /* 5:4, access type */
-#define CONTROL_REG_ACCESS_REG          0xf00   /* 10:8, general purpose register */
+#define CONTROL_REG_ACCESS_REG          0xf00   /* 10:8, general purpose reg. */
 #define LMSW_SOURCE_DATA_SHIFT 16
 #define LMSW_SOURCE_DATA  (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */
 #define REG_EAX                         (0 << 8)
@@ -259,11 +271,11 @@ enum vmcs_field {
 /*
  * Exit Qualifications for MOV for Debug Register Access
  */
-#define DEBUG_REG_ACCESS_NUM            0x7     /* 2:0, number of debug register */
+#define DEBUG_REG_ACCESS_NUM            0x7     /* 2:0, number of debug reg. */
 #define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
 #define TYPE_MOV_TO_DR                  (0 << 4)
 #define TYPE_MOV_FROM_DR                (1 << 4)
-#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose register */
+#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
 
 
 /* segment AR */
@@ -307,4 +319,6 @@ enum vmcs_field {
 #define MSR_IA32_FEATURE_CONTROL_LOCKED         0x1
 #define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED  0x4
 
+#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	9
+
 #endif

drivers/Kconfig

@@ -90,8 +90,6 @@ source "drivers/dca/Kconfig"
 
 source "drivers/auxdisplay/Kconfig"
 
-source "drivers/kvm/Kconfig"
-
 source "drivers/uio/Kconfig"
 
 source "drivers/virtio/Kconfig"

drivers/Makefile

@@ -47,7 +47,6 @@ obj-$(CONFIG_SPI)		+= spi/
 obj-$(CONFIG_PCCARD)		+= pcmcia/
 obj-$(CONFIG_DIO)		+= dio/
 obj-$(CONFIG_SBUS)		+= sbus/
-obj-$(CONFIG_KVM)		+= kvm/
 obj-$(CONFIG_ZORRO)		+= zorro/
 obj-$(CONFIG_MAC)		+= macintosh/
 obj-$(CONFIG_ATA_OVER_ETH)	+= block/aoe/

include/asm-x86/Kbuild

@@ -3,6 +3,7 @@ include include/asm-generic/Kbuild.asm
 header-y += boot.h
 header-y += bootparam.h
 header-y += debugreg.h
+header-y += kvm.h
 header-y += ldt.h
 header-y += msr-index.h
 header-y += prctl.h

include/asm-x86/kvm.h

+#ifndef __LINUX_KVM_X86_H
+#define __LINUX_KVM_X86_H
+
+/*
+ * KVM x86 specific structures and definitions
+ *
+ */
+
+#include <asm/types.h>
+#include <linux/ioctl.h>
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+struct kvm_memory_alias {
+	__u32 slot;  /* this has a different namespace than memory slots */
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 target_phys_addr;
+};
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+	__u8 last_irr;	/* edge detection */
+	__u8 irr;		/* interrupt request register */
+	__u8 imr;		/* interrupt mask register */
+	__u8 isr;		/* interrupt service register */
+	__u8 priority_add;	/* highest irq priority */
+	__u8 irq_base;
+	__u8 read_reg_select;
+	__u8 poll;
+	__u8 special_mask;
+	__u8 init_state;
+	__u8 auto_eoi;
+	__u8 rotate_on_auto_eoi;
+	__u8 special_fully_nested_mode;
+	__u8 init4;		/* true if 4 byte init */
+	__u8 elcr;		/* PIIX edge/trigger selection */
+	__u8 elcr_mask;
+};
+
+#define KVM_IOAPIC_NUM_PINS  24
+struct kvm_ioapic_state {
+	__u64 base_address;
+	__u32 ioregsel;
+	__u32 id;
+	__u32 irr;
+	__u32 pad;
+	union {
+		__u64 bits;
+		struct {
+			__u8 vector;
+			__u8 delivery_mode:3;
+			__u8 dest_mode:1;
+			__u8 delivery_status:1;
+			__u8 polarity:1;
+			__u8 remote_irr:1;
+			__u8 trig_mode:1;
+			__u8 mask:1;
+			__u8 reserve:7;
+			__u8 reserved[4];
+			__u8 dest_id;
+		} fields;
+	} redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER   0
+#define KVM_IRQCHIP_PIC_SLAVE    1
+#define KVM_IRQCHIP_IOAPIC       2
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 rax, rbx, rcx, rdx;
+	__u64 rsi, rdi, rsp, rbp;
+	__u64 r8,  r9,  r10, r11;
+	__u64 r12, r13, r14, r15;
+	__u64 rip, rflags;
+};
+
+/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+	char regs[KVM_APIC_REG_SIZE];
+};
+
+struct kvm_segment {
+	__u64 base;
+	__u32 limit;
+	__u16 selector;
+	__u8  type;
+	__u8  present, dpl, db, s, l, g, avl;
+	__u8  unusable;
+	__u8  padding;
+};
+
+struct kvm_dtable {
+	__u64 base;
+	__u16 limit;
+	__u16 padding[3];
+};
+
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
+	struct kvm_segment cs, ds, es, fs, gs, ss;
+	struct kvm_segment tr, ldt;
+	struct kvm_dtable gdt, idt;
+	__u64 cr0, cr2, cr3, cr4, cr8;
+	__u64 efer;
+	__u64 apic_base;
+	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u8  fpr[8][16];
+	__u16 fcw;
+	__u16 fsw;
+	__u8  ftwx;  /* in fxsave format */
+	__u8  pad1;
+	__u16 last_opcode;
+	__u64 last_ip;
+	__u64 last_dp;
+	__u8  xmm[16][16];
+	__u32 mxcsr;
+	__u32 pad2;
+};
+
+struct kvm_msr_entry {
+	__u32 index;
+	__u32 reserved;
+	__u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 pad;
+
+	struct kvm_msr_entry entries[0];
+};
+
+/* for KVM_GET_MSR_INDEX_LIST */
+struct kvm_msr_list {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 indices[0];
+};
+
+
+struct kvm_cpuid_entry {
+	__u32 function;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
+#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
+#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+
+/* for KVM_SET_CPUID2 */
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+#endif

include/asm-x86/kvm_para.h

+#ifndef __X86_KVM_PARA_H
+#define __X86_KVM_PARA_H
+
+/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
+ * should be used to determine that a VM is running under KVM.
+ */
+#define KVM_CPUID_SIGNATURE	0x40000000
+
+/* This CPUID returns a feature bitmap in eax.  Before enabling a particular
+ * paravirtualization, the appropriate feature bit should be checked.
+ */
+#define KVM_CPUID_FEATURES	0x40000001
+
+#ifdef __KERNEL__
+#include <asm/processor.h>
+
+/* This instruction is vmcall.  On non-VT architectures, it will generate a
+ * trap that we will then rewrite to the appropriate instruction.
+ */
+#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+
+/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
+ * instruction.  The hypervisor may replace it with something else but only the
+ * instructions are guaranteed to be supported.
+ *
+ * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ * The hypercall number should be placed in rax and the return value will be
+ * placed in rax.  No other registers will be clobbered unless explicited
+ * noted by the particular hypercall.
+ */
+
+static inline long kvm_hypercall0(unsigned int nr)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr));
+	return ret;
+}
+
+static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1));
+	return ret;
+}
+
+static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
+				  unsigned long p2)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2));
+	return ret;
+}
+
+static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3));
+	return ret;
+}
+
+static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3,
+				  unsigned long p4)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4));
+	return ret;
+}
+
+static inline int kvm_para_available(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	char signature[13];
+
+	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
+	memcpy(signature + 0, &ebx, 4);
+	memcpy(signature + 4, &ecx, 4);
+	memcpy(signature + 8, &edx, 4);
+	signature[12] = 0;
+
+	if (strcmp(signature, "KVMKVMKVM") == 0)
+		return 1;
+
+	return 0;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return cpuid_eax(KVM_CPUID_FEATURES);
+}
+
+#endif
+
+#endif

drivers/kvm/x86_emulate.h → include/asm-x86/kvm_x86_emulate.h

@@ -62,17 +62,6 @@ struct x86_emulate_ops {
 	int (*read_std)(unsigned long addr, void *val,
 			unsigned int bytes, struct kvm_vcpu *vcpu);
 
-	/*
-	 * write_std: Write bytes of standard (non-emulated/special) memory.
-	 *            Used for stack operations, and others.
-	 *  @addr:  [IN ] Linear address to which to write.
-	 *  @val:   [IN ] Value to write to memory (low-order bytes used as
-	 *                required).
-	 *  @bytes: [IN ] Number of bytes to write to memory.
-	 */
-	int (*write_std)(unsigned long addr, const void *val,
-			 unsigned int bytes, struct kvm_vcpu *vcpu);
-
 	/*
 	 * read_emulated: Read bytes from emulated/special memory area.
 	 *  @addr:  [IN ] Linear address from which to read.
@@ -112,13 +101,50 @@ struct x86_emulate_ops {
 
 };
 
+/* Type, address-of, and value of an instruction's operand. */
+struct operand {
+	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
+	unsigned int bytes;
+	unsigned long val, orig_val, *ptr;
+};
+
+struct fetch_cache {
+	u8 data[15];
+	unsigned long start;
+	unsigned long end;
+};
+
+struct decode_cache {
+	u8 twobyte;
+	u8 b;
+	u8 lock_prefix;
+	u8 rep_prefix;
+	u8 op_bytes;
+	u8 ad_bytes;
+	u8 rex_prefix;
+	struct operand src;
+	struct operand dst;
+	unsigned long *override_base;
+	unsigned int d;
+	unsigned long regs[NR_VCPU_REGS];
+	unsigned long eip;
+	/* modrm */
+	u8 modrm;
+	u8 modrm_mod;
+	u8 modrm_reg;
+	u8 modrm_rm;
+	u8 use_modrm_ea;
+	unsigned long modrm_ea;
+	unsigned long modrm_val;
+	struct fetch_cache fetch;
+};
+
 struct x86_emulate_ctxt {
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
 
 	/* Linear faulting address (if emulating a page-faulting instruction). */
 	unsigned long eflags;
-	unsigned long cr2;
 
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
@@ -129,8 +155,16 @@ struct x86_emulate_ctxt {
 	unsigned long ss_base;
 	unsigned long gs_base;
 	unsigned long fs_base;
+
+	/* decode cache */
+
+	struct decode_cache decode;
 };
 
+/* Repeat String Operation Prefix */
+#define REPE_PREFIX  1
+#define REPNE_PREFIX    2
+
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0	/* Real mode.             */
 #define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
@@ -144,12 +178,9 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-/*
- * x86_emulate_memop: Emulate an instruction that faulted attempting to
- *                    read/write a 'special' memory area.
- * Returns -1 on failure, 0 on success.
- */
-int x86_emulate_memop(struct x86_emulate_ctxt *ctxt,
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
+		    struct x86_emulate_ops *ops);
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
 		     struct x86_emulate_ops *ops);
 
 #endif				/* __X86_EMULATE_H__ */

include/linux/Kbuild

@@ -100,7 +100,6 @@ header-y += iso_fs.h
 header-y += ixjuser.h
 header-y += jffs2.h
 header-y += keyctl.h
-header-y += kvm.h
 header-y += limits.h
 header-y += lock_dlm_plock.h
 header-y += magic.h
@@ -256,6 +255,7 @@ unifdef-y += kd.h
 unifdef-y += kernelcapi.h
 unifdef-y += kernel.h
 unifdef-y += keyboard.h
+unifdef-$(CONFIG_HAVE_KVM) += kvm.h
 unifdef-y += llc.h
 unifdef-y += loop.h
 unifdef-y += lp.h

include/linux/kvm.h

@@ -9,12 +9,10 @@
 
 #include <asm/types.h>
 #include <linux/ioctl.h>
+#include <asm/kvm.h>
 
 #define KVM_API_VERSION 12
 
-/* Architectural interrupt line count. */
-#define KVM_NR_INTERRUPTS 256
-
 /* for KVM_CREATE_MEMORY_REGION */
 struct kvm_memory_region {
 	__u32 slot;
@@ -23,17 +21,19 @@ struct kvm_memory_region {
 	__u64 memory_size; /* bytes */
 };
 
-/* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES  1UL
-
-struct kvm_memory_alias {
-	__u32 slot;  /* this has a different namespace than memory slots */
+/* for KVM_SET_USER_MEMORY_REGION */
+struct kvm_userspace_memory_region {
+	__u32 slot;
 	__u32 flags;
 	__u64 guest_phys_addr;
-	__u64 memory_size;
-	__u64 target_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for kvm_memory_region::flags */
+#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+
+
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
 	/*
@@ -45,62 +45,18 @@ struct kvm_irq_level {
 	__u32 level;
 };
 
-/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
-struct kvm_pic_state {
-	__u8 last_irr;	/* edge detection */
-	__u8 irr;		/* interrupt request register */
-	__u8 imr;		/* interrupt mask register */
-	__u8 isr;		/* interrupt service register */
-	__u8 priority_add;	/* highest irq priority */
-	__u8 irq_base;
-	__u8 read_reg_select;
-	__u8 poll;
-	__u8 special_mask;
-	__u8 init_state;
-	__u8 auto_eoi;
-	__u8 rotate_on_auto_eoi;
-	__u8 special_fully_nested_mode;
-	__u8 init4;		/* true if 4 byte init */
-	__u8 elcr;		/* PIIX edge/trigger selection */
-	__u8 elcr_mask;
-};
-
-#define KVM_IOAPIC_NUM_PINS  24
-struct kvm_ioapic_state {
-	__u64 base_address;
-	__u32 ioregsel;
-	__u32 id;
-	__u32 irr;
-	__u32 pad;
-	union {
-		__u64 bits;
-		struct {
-			__u8 vector;
-			__u8 delivery_mode:3;
-			__u8 dest_mode:1;
-			__u8 delivery_status:1;
-			__u8 polarity:1;
-			__u8 remote_irr:1;
-			__u8 trig_mode:1;
-			__u8 mask:1;
-			__u8 reserve:7;
-			__u8 reserved[4];
-			__u8 dest_id;
-		} fields;
-	} redirtbl[KVM_IOAPIC_NUM_PINS];
-};
-
-#define KVM_IRQCHIP_PIC_MASTER   0
-#define KVM_IRQCHIP_PIC_SLAVE    1
-#define KVM_IRQCHIP_IOAPIC       2
 
 struct kvm_irqchip {
 	__u32 chip_id;
 	__u32 pad;
         union {
 		char dummy[512];  /* reserving space */
+#ifdef CONFIG_X86
 		struct kvm_pic_state pic;
+#endif
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
 		struct kvm_ioapic_state ioapic;
+#endif
 	} chip;
 };
 
@@ -116,6 +72,7 @@ struct kvm_irqchip {
 #define KVM_EXIT_FAIL_ENTRY       9
 #define KVM_EXIT_INTR             10
 #define KVM_EXIT_SET_TPR          11
+#define KVM_EXIT_TPR_ACCESS       12
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -174,90 +131,17 @@ struct kvm_run {
 			__u32 longmode;
 			__u32 pad;
 		} hypercall;
+		/* KVM_EXIT_TPR_ACCESS */
+		struct {
+			__u64 rip;
+			__u32 is_write;
+			__u32 pad;
+		} tpr_access;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
 };
 
-/* for KVM_GET_REGS and KVM_SET_REGS */
-struct kvm_regs {
-	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
-	__u64 rax, rbx, rcx, rdx;
-	__u64 rsi, rdi, rsp, rbp;
-	__u64 r8,  r9,  r10, r11;
-	__u64 r12, r13, r14, r15;
-	__u64 rip, rflags;
-};
-
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
-	__u8  fpr[8][16];
-	__u16 fcw;
-	__u16 fsw;
-	__u8  ftwx;  /* in fxsave format */
-	__u8  pad1;
-	__u16 last_opcode;
-	__u64 last_ip;
-	__u64 last_dp;
-	__u8  xmm[16][16];
-	__u32 mxcsr;
-	__u32 pad2;
-};
-
-/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
-	char regs[KVM_APIC_REG_SIZE];
-};
-
-struct kvm_segment {
-	__u64 base;
-	__u32 limit;
-	__u16 selector;
-	__u8  type;
-	__u8  present, dpl, db, s, l, g, avl;
-	__u8  unusable;
-	__u8  padding;
-};
-
-struct kvm_dtable {
-	__u64 base;
-	__u16 limit;
-	__u16 padding[3];
-};
-
-/* for KVM_GET_SREGS and KVM_SET_SREGS */
-struct kvm_sregs {
-	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
-	struct kvm_segment cs, ds, es, fs, gs, ss;
-	struct kvm_segment tr, ldt;
-	struct kvm_dtable gdt, idt;
-	__u64 cr0, cr2, cr3, cr4, cr8;
-	__u64 efer;
-	__u64 apic_base;
-	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
-};
-
-struct kvm_msr_entry {
-	__u32 index;
-	__u32 reserved;
-	__u64 data;
-};
-
-/* for KVM_GET_MSRS and KVM_SET_MSRS */
-struct kvm_msrs {
-	__u32 nmsrs; /* number of msrs in entries */
-	__u32 pad;
-
-	struct kvm_msr_entry entries[0];
-};
-
-/* for KVM_GET_MSR_INDEX_LIST */
-struct kvm_msr_list {
-	__u32 nmsrs; /* number of msrs in entries */
-	__u32 indices[0];
-};
-
 /* for KVM_TRANSLATE */
 struct kvm_translation {
 	/* in */
@@ -302,28 +186,24 @@ struct kvm_dirty_log {
 	};
 };
 
-struct kvm_cpuid_entry {
-	__u32 function;
-	__u32 eax;
-	__u32 ebx;
-	__u32 ecx;
-	__u32 edx;
-	__u32 padding;
-};
-
-/* for KVM_SET_CPUID */
-struct kvm_cpuid {
-	__u32 nent;
-	__u32 padding;
-	struct kvm_cpuid_entry entries[0];
-};
-
 /* for KVM_SET_SIGNAL_MASK */
 struct kvm_signal_mask {
 	__u32 len;
 	__u8  sigset[0];
 };
 
+/* for KVM_TPR_ACCESS_REPORTING */
+struct kvm_tpr_access_ctl {
+	__u32 enabled;
+	__u32 flags;
+	__u32 reserved[8];
+};
+
+/* for KVM_SET_VAPIC_ADDR */
+struct kvm_vapic_addr {
+	__u64 vapic_addr;
+};
+
 #define KVMIO 0xAE
 
 /*
@@ -347,11 +227,21 @@ struct kvm_signal_mask {
  */
 #define KVM_CAP_IRQCHIP	  0
 #define KVM_CAP_HLT	  1
+#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2
+#define KVM_CAP_USER_MEMORY 3
+#define KVM_CAP_SET_TSS_ADDR 4
+#define KVM_CAP_EXT_CPUID 5
+#define KVM_CAP_VAPIC 6
 
 /*
  * ioctls for VM fds
  */
 #define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 0x40, struct kvm_memory_region)
+#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO, 0x44)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO, 0x45)
+#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\
+					struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR          _IO(KVMIO, 0x47)
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
@@ -359,6 +249,7 @@ struct kvm_signal_mask {
 #define KVM_CREATE_VCPU           _IO(KVMIO,  0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 0x42, struct kvm_dirty_log)
 #define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO, 0x43, struct kvm_memory_alias)
+#define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x48, struct kvm_cpuid2)
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP	  _IO(KVMIO,  0x60)
 #define KVM_IRQ_LINE		  _IOW(KVMIO, 0x61, struct kvm_irq_level)
@@ -384,5 +275,11 @@ struct kvm_signal_mask {
 #define KVM_SET_FPU               _IOW(KVMIO,  0x8d, struct kvm_fpu)
 #define KVM_GET_LAPIC             _IOR(KVMIO,  0x8e, struct kvm_lapic_state)
 #define KVM_SET_LAPIC             _IOW(KVMIO,  0x8f, struct kvm_lapic_state)
+#define KVM_SET_CPUID2            _IOW(KVMIO,  0x90, struct kvm_cpuid2)
+#define KVM_GET_CPUID2            _IOWR(KVMIO, 0x91, struct kvm_cpuid2)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_TPR_ACCESS_REPORTING  _IOWR(KVMIO,  0x92, struct kvm_tpr_access_ctl)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_SET_VAPIC_ADDR        _IOW(KVMIO,  0x93, struct kvm_vapic_addr)
 
 #endif

include/linux/kvm_para.h

@@ -2,72 +2,30 @@
 #define __LINUX_KVM_PARA_H
 
 /*
- * Guest OS interface for KVM paravirtualization
- *
- * Note: this interface is totally experimental, and is certain to change
- *       as we make progress.
+ * This header file provides a method for making a hypercall to the host
+ * Architectures should define:
+ * - kvm_hypercall0, kvm_hypercall1...
+ * - kvm_arch_para_features
+ * - kvm_para_available
  */
 
-/*
- * Per-VCPU descriptor area shared between guest and host. Writable to
- * both guest and host. Registered with the host by the guest when
- * a guest acknowledges paravirtual mode.
- *
- * NOTE: all addresses are guest-physical addresses (gpa), to make it
- * easier for the hypervisor to map between the various addresses.
- */
-struct kvm_vcpu_para_state {
-	/*
-	 * API version information for compatibility. If there's any support
-	 * mismatch (too old host trying to execute too new guest) then
-	 * the host will deny entry into paravirtual mode. Any other
-	 * combination (new host + old guest and new host + new guest)
-	 * is supposed to work - new host versions will support all old
-	 * guest API versions.
-	 */
-	u32 guest_version;
-	u32 host_version;
-	u32 size;
-	u32 ret;
-
-	/*
-	 * The address of the vm exit instruction (VMCALL or VMMCALL),
-	 * which the host will patch according to the CPU model the
-	 * VM runs on:
-	 */
-	u64 hypercall_gpa;
-
-} __attribute__ ((aligned(PAGE_SIZE)));
-
-#define KVM_PARA_API_VERSION 1
-
-/*
- * This is used for an RDMSR's ECX parameter to probe for a KVM host.
- * Hopefully no CPU vendor will use up this number. This is placed well
- * out of way of the typical space occupied by CPU vendors' MSR indices,
- * and we think (or at least hope) it wont be occupied in the future
- * either.
- */
-#define MSR_KVM_API_MAGIC 0x87655678
+/* Return values for hypercalls */
+#define KVM_ENOSYS		1000
 
-#define KVM_EINVAL 1
+#define KVM_HC_VAPIC_POLL_IRQ            1
 
 /*
- * Hypercall calling convention:
- *
- * Each hypercall may have 0-6 parameters.
- *
- * 64-bit hypercall index is in RAX, goes from 0 to __NR_hypercalls-1
- *
- * 64-bit parameters 1-6 are in the standard gcc x86_64 calling convention
- * order: RDI, RSI, RDX, RCX, R8, R9.
- *
- * 32-bit index is EBX, parameters are: EAX, ECX, EDX, ESI, EDI, EBP.
- * (the first 3 are according to the gcc regparm calling convention)
- *
- * No registers are clobbered by the hypercall, except that the
- * return value is in RAX.
+ * hypercalls use architecture specific
  */
-#define __NR_hypercalls			0
+#include <asm/kvm_para.h>
+
+#ifdef __KERNEL__
+static inline int kvm_para_has_feature(unsigned int feature)
+{
+	if (kvm_arch_para_features() & (1UL << feature))
+		return 1;
+	return 0;
+}
+#endif /* __KERNEL__ */
+#endif /* __LINUX_KVM_PARA_H */
 
-#endif

kernel/fork.c

@@ -393,6 +393,7 @@ void fastcall __mmdrop(struct mm_struct *mm)
 	destroy_context(mm);
 	free_mm(mm);
 }
+EXPORT_SYMBOL_GPL(__mmdrop);
 
 /*
  * Decrement the use count and release all resources for an mm.