[PATCH] kvm: userspace interface

web site: http://kvm.sourceforge.net

mailing list: kvm-devel@lists.sourceforge.net
  (http://lists.sourceforge.net/lists/listinfo/kvm-devel)

The following patchset adds a driver for Intel's hardware virtualization
extensions to the x86 architecture.  The driver adds a character device
(/dev/kvm) that exposes the virtualization capabilities to userspace.  Using
this driver, a process can run a virtual machine (a "guest") in a fully
virtualized PC containing its own virtual hard disks, network adapters, and
display.

Using this driver, one can start multiple virtual machines on a host.

Each virtual machine is a process on the host; a virtual cpu is a thread in
that process.  kill(1), nice(1), top(1) work as expected.  In effect, the
driver adds a third execution mode to the existing two: we now have kernel
mode, user mode, and guest mode.  Guest mode has its own address space mapping
guest physical memory (which is accessible to user mode by mmap()ing
/dev/kvm).  Guest mode has no access to any I/O devices; any such access is
intercepted and directed to user mode for emulation.

The driver supports i386 and x86_64 hosts and guests.  All combinations are
allowed except x86_64 guest on i386 host.  For i386 guests and hosts, both pae
and non-pae paging modes are supported.

SMP hosts and UP guests are supported.  At the moment only Intel
hardware is supported, but AMD virtualization support is being worked on.

Performance currently is non-stellar due to the naive implementation of the
mmu virtualization, which throws away most of the shadow page table entries
every context switch.  We plan to address this in two ways:

- cache shadow page tables across tlb flushes
- wait until AMD and Intel release processors with nested page tables

Currently a virtual desktop is responsive but consumes a lot of CPU.  Under
Windows I tried playing pinball and watching a few flash movies; with a recent
CPU one can hardly feel the virtualization.  Linux/X is slower, probably due
to X being in a separate process.

In addition to the driver, you need a slightly modified qemu to provide I/O
device emulation and the BIOS.

Caveats (akpm: might no longer be true):

- The Windows install currently bluescreens due to a problem with the
  virtual APIC.  We are working on a fix.  A temporary workaround is to
  use an existing image or install through qemu
- Windows 64-bit does not work.  That's also true for qemu, so it's
  probably a problem with the device model.

[bero@arklinux.org: build fix]
[simon.kagstrom@bth.se: build fix, other fixes]
[uril@qumranet.com: KVM: Expose interrupt bitmap]
[akpm@osdl.org: i386 build fix]
[mingo@elte.hu: i386 fixes]
[rdreier@cisco.com: add log levels to all printks]
[randy.dunlap@oracle.com: Fix sparse NULL and C99 struct init warnings]
[anthony@codemonkey.ws: KVM: AMD SVM: 32-bit host support]
Signed-off-by: Yaniv Kamay <yaniv@qumranet.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Cc: Simon Kagstrom <simon.kagstrom@bth.se>
Cc: Bernhard Rosenkraenzer <bero@arklinux.org>
Signed-off-by: Uri Lublin <uril@qumranet.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Anthony Liguori <anthony@codemonkey.ws>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/Kconfig

@@ -80,4 +80,6 @@ source "drivers/rtc/Kconfig"
 
 source "drivers/dma/Kconfig"
 
+source "drivers/kvm/Kconfig"
+
 endmenu

drivers/Makefile

@@ -43,6 +43,7 @@ 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/

drivers/kvm/Kconfig

+#
+# KVM configuration
+#
+config KVM
+	tristate "Kernel-based Virtual Machine (KVM) support"
+	depends on X86 && EXPERIMENTAL
+	---help---
+	  Support hosting fully virtualized guest machines using hardware
+	  virtualization extensions.  You will need a fairly recent
+	  processor equipped with virtualization extensions. You will also
+	  need to select one or more of the processor modules below.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  To compile this as a module, choose M here: the module
+	  will be called kvm.
+
+	  If unsure, say N.
+
+config KVM_INTEL
+	tristate "KVM for Intel processors support"
+	depends on KVM
+	---help---
+	  Provides support for KVM on Intel processors equipped with the VT
+	  extensions.
+
+config KVM_AMD
+	tristate "KVM for AMD processors support"
+	depends on KVM
+	---help---
+	  Provides support for KVM on AMD processors equipped with the AMD-V
+	  (SVM) extensions.

drivers/kvm/Makefile

+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+kvm-objs := kvm_main.o mmu.o x86_emulate.o
+obj-$(CONFIG_KVM) += kvm.o
+kvm-intel-objs = vmx.o
+obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
+kvm-amd-objs = svm.o
+obj-$(CONFIG_KVM_AMD) += kvm-amd.o

drivers/kvm/kvm_svm.h

+#ifndef __KVM_SVM_H
+#define __KVM_SVM_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <asm/msr.h>
+
+#include "svm.h"
+#include "kvm.h"
+
+static const u32 host_save_msrs[] = {
+#ifdef __x86_64__
+	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
+	MSR_FS_BASE, MSR_GS_BASE,
+#endif
+	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
+	MSR_IA32_DEBUGCTLMSR, /*MSR_IA32_LASTBRANCHFROMIP,
+	MSR_IA32_LASTBRANCHTOIP, MSR_IA32_LASTINTFROMIP,MSR_IA32_LASTINTTOIP,*/
+};
+
+#define NR_HOST_SAVE_MSRS (sizeof(host_save_msrs) / sizeof(*host_save_msrs))
+#define NUM_DB_REGS 4
+
+struct vcpu_svm {
+	struct vmcb *vmcb;
+	unsigned long vmcb_pa;
+	struct svm_cpu_data *svm_data;
+	uint64_t asid_generation;
+
+	unsigned long cr0;
+	unsigned long cr4;
+	unsigned long db_regs[NUM_DB_REGS];
+
+	u64 next_rip;
+
+	u64 host_msrs[NR_HOST_SAVE_MSRS];
+	unsigned long host_cr2;
+	unsigned long host_db_regs[NUM_DB_REGS];
+	unsigned long host_dr6;
+	unsigned long host_dr7;
+};
+
+#endif
+

drivers/kvm/kvm_vmx.h

+#ifndef __KVM_VMX_H
+#define __KVM_VMX_H
+
+#ifdef __x86_64__
+/*
+ * avoid save/load MSR_SYSCALL_MASK and MSR_LSTAR by std vt
+ * mechanism (cpu bug AA24)
+ */
+#define NR_BAD_MSRS 2
+#else
+#define NR_BAD_MSRS 0
+#endif
+
+#endif

drivers/kvm/segment_descriptor.h

+struct segment_descriptor {
+	u16 limit_low;
+	u16 base_low;
+	u8  base_mid;
+	u8  type : 4;
+	u8  system : 1;
+	u8  dpl : 2;
+	u8  present : 1;
+	u8  limit_high : 4;
+	u8  avl : 1;
+	u8  long_mode : 1;
+	u8  default_op : 1;
+	u8  granularity : 1;
+	u8  base_high;
+} __attribute__((packed));
+
+

drivers/kvm/svm.h

+#ifndef __SVM_H
+#define __SVM_H
+
+enum {
+	INTERCEPT_INTR,
+	INTERCEPT_NMI,
+	INTERCEPT_SMI,
+	INTERCEPT_INIT,
+	INTERCEPT_VINTR,
+	INTERCEPT_SELECTIVE_CR0,
+	INTERCEPT_STORE_IDTR,
+	INTERCEPT_STORE_GDTR,
+	INTERCEPT_STORE_LDTR,
+	INTERCEPT_STORE_TR,
+	INTERCEPT_LOAD_IDTR,
+	INTERCEPT_LOAD_GDTR,
+	INTERCEPT_LOAD_LDTR,
+	INTERCEPT_LOAD_TR,
+	INTERCEPT_RDTSC,
+	INTERCEPT_RDPMC,
+	INTERCEPT_PUSHF,
+	INTERCEPT_POPF,
+	INTERCEPT_CPUID,
+	INTERCEPT_RSM,
+	INTERCEPT_IRET,
+	INTERCEPT_INTn,
+	INTERCEPT_INVD,
+	INTERCEPT_PAUSE,
+	INTERCEPT_HLT,
+	INTERCEPT_INVLPG,
+	INTERCEPT_INVLPGA,
+	INTERCEPT_IOIO_PROT,
+	INTERCEPT_MSR_PROT,
+	INTERCEPT_TASK_SWITCH,
+	INTERCEPT_FERR_FREEZE,
+	INTERCEPT_SHUTDOWN,
+	INTERCEPT_VMRUN,
+	INTERCEPT_VMMCALL,
+	INTERCEPT_VMLOAD,
+	INTERCEPT_VMSAVE,
+	INTERCEPT_STGI,
+	INTERCEPT_CLGI,
+	INTERCEPT_SKINIT,
+	INTERCEPT_RDTSCP,
+	INTERCEPT_ICEBP,
+	INTERCEPT_WBINVD,
+};
+
+
+struct __attribute__ ((__packed__)) vmcb_control_area {
+	u16 intercept_cr_read;
+	u16 intercept_cr_write;
+	u16 intercept_dr_read;
+	u16 intercept_dr_write;
+	u32 intercept_exceptions;
+	u64 intercept;
+	u8 reserved_1[44];
+	u64 iopm_base_pa;
+	u64 msrpm_base_pa;
+	u64 tsc_offset;
+	u32 asid;
+	u8 tlb_ctl;
+	u8 reserved_2[3];
+	u32 int_ctl;
+	u32 int_vector;
+	u32 int_state;
+	u8 reserved_3[4];
+	u32 exit_code;
+	u32 exit_code_hi;
+	u64 exit_info_1;
+	u64 exit_info_2;
+	u32 exit_int_info;
+	u32 exit_int_info_err;
+	u64 nested_ctl;
+	u8 reserved_4[16];
+	u32 event_inj;
+	u32 event_inj_err;
+	u64 nested_cr3;
+	u64 lbr_ctl;
+	u8 reserved_5[832];
+};
+
+
+#define TLB_CONTROL_DO_NOTHING 0
+#define TLB_CONTROL_FLUSH_ALL_ASID 1
+
+#define V_TPR_MASK 0x0f
+
+#define V_IRQ_SHIFT 8
+#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+
+#define V_INTR_PRIO_SHIFT 16
+#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
+
+#define V_IGN_TPR_SHIFT 20
+#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+
+#define V_INTR_MASKING_SHIFT 24
+#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+
+#define SVM_INTERRUPT_SHADOW_MASK 1
+
+#define SVM_IOIO_STR_SHIFT 2
+#define SVM_IOIO_REP_SHIFT 3
+#define SVM_IOIO_SIZE_SHIFT 4
+#define SVM_IOIO_ASIZE_SHIFT 7
+
+#define SVM_IOIO_TYPE_MASK 1
+#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
+#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
+#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
+#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
+
+struct __attribute__ ((__packed__)) vmcb_seg {
+	u16 selector;
+	u16 attrib;
+	u32 limit;
+	u64 base;
+};
+
+struct __attribute__ ((__packed__)) vmcb_save_area {
+	struct vmcb_seg es;
+	struct vmcb_seg cs;
+	struct vmcb_seg ss;
+	struct vmcb_seg ds;
+	struct vmcb_seg fs;
+	struct vmcb_seg gs;
+	struct vmcb_seg gdtr;
+	struct vmcb_seg ldtr;
+	struct vmcb_seg idtr;
+	struct vmcb_seg tr;
+	u8 reserved_1[43];
+	u8 cpl;
+	u8 reserved_2[4];
+	u64 efer;
+	u8 reserved_3[112];
+	u64 cr4;
+	u64 cr3;
+	u64 cr0;
+	u64 dr7;
+	u64 dr6;
+	u64 rflags;
+	u64 rip;
+	u8 reserved_4[88];
+	u64 rsp;
+	u8 reserved_5[24];
+	u64 rax;
+	u64 star;
+	u64 lstar;
+	u64 cstar;
+	u64 sfmask;
+	u64 kernel_gs_base;
+	u64 sysenter_cs;
+	u64 sysenter_esp;
+	u64 sysenter_eip;
+	u64 cr2;
+	u8 reserved_6[32];
+	u64 g_pat;
+	u64 dbgctl;
+	u64 br_from;
+	u64 br_to;
+	u64 last_excp_from;
+	u64 last_excp_to;
+};
+
+struct __attribute__ ((__packed__)) vmcb {
+	struct vmcb_control_area control;
+	struct vmcb_save_area save;
+};
+
+#define SVM_CPUID_FEATURE_SHIFT 2
+#define SVM_CPUID_FUNC 0x8000000a
+
+#define MSR_EFER_SVME_MASK (1ULL << 12)
+#define MSR_VM_HSAVE_PA 0xc0010117ULL
+
+#define SVM_SELECTOR_S_SHIFT 4
+#define SVM_SELECTOR_DPL_SHIFT 5
+#define SVM_SELECTOR_P_SHIFT 7
+#define SVM_SELECTOR_AVL_SHIFT 8
+#define SVM_SELECTOR_L_SHIFT 9
+#define SVM_SELECTOR_DB_SHIFT 10
+#define SVM_SELECTOR_G_SHIFT 11
+
+#define SVM_SELECTOR_TYPE_MASK (0xf)
+#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
+#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
+#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
+#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
+#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
+#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
+#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
+
+#define SVM_SELECTOR_WRITE_MASK (1 << 1)
+#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
+#define SVM_SELECTOR_CODE_MASK (1 << 3)
+
+#define INTERCEPT_CR0_MASK 1
+#define INTERCEPT_CR3_MASK (1 << 3)
+#define INTERCEPT_CR4_MASK (1 << 4)
+
+#define INTERCEPT_DR0_MASK 1
+#define INTERCEPT_DR1_MASK (1 << 1)
+#define INTERCEPT_DR2_MASK (1 << 2)
+#define INTERCEPT_DR3_MASK (1 << 3)
+#define INTERCEPT_DR4_MASK (1 << 4)
+#define INTERCEPT_DR5_MASK (1 << 5)
+#define INTERCEPT_DR6_MASK (1 << 6)
+#define INTERCEPT_DR7_MASK (1 << 7)
+
+#define SVM_EVTINJ_VEC_MASK 0xff
+
+#define SVM_EVTINJ_TYPE_SHIFT 8
+#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_VALID (1 << 31)
+#define SVM_EVTINJ_VALID_ERR (1 << 11)
+
+#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+
+#define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
+#define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
+#define	SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
+#define	SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
+
+#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
+#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+
+#define	SVM_EXIT_READ_CR0 	0x000
+#define	SVM_EXIT_READ_CR3 	0x003
+#define	SVM_EXIT_READ_CR4 	0x004
+#define	SVM_EXIT_READ_CR8 	0x008
+#define	SVM_EXIT_WRITE_CR0 	0x010
+#define	SVM_EXIT_WRITE_CR3 	0x013
+#define	SVM_EXIT_WRITE_CR4 	0x014
+#define	SVM_EXIT_WRITE_CR8 	0x018
+#define	SVM_EXIT_READ_DR0 	0x020
+#define	SVM_EXIT_READ_DR1 	0x021
+#define	SVM_EXIT_READ_DR2 	0x022
+#define	SVM_EXIT_READ_DR3 	0x023
+#define	SVM_EXIT_READ_DR4 	0x024
+#define	SVM_EXIT_READ_DR5 	0x025
+#define	SVM_EXIT_READ_DR6 	0x026
+#define	SVM_EXIT_READ_DR7 	0x027
+#define	SVM_EXIT_WRITE_DR0 	0x030
+#define	SVM_EXIT_WRITE_DR1 	0x031
+#define	SVM_EXIT_WRITE_DR2 	0x032
+#define	SVM_EXIT_WRITE_DR3 	0x033
+#define	SVM_EXIT_WRITE_DR4 	0x034
+#define	SVM_EXIT_WRITE_DR5 	0x035
+#define	SVM_EXIT_WRITE_DR6 	0x036
+#define	SVM_EXIT_WRITE_DR7 	0x037
+#define SVM_EXIT_EXCP_BASE      0x040
+#define SVM_EXIT_INTR		0x060
+#define SVM_EXIT_NMI		0x061
+#define SVM_EXIT_SMI		0x062
+#define SVM_EXIT_INIT		0x063
+#define SVM_EXIT_VINTR		0x064
+#define SVM_EXIT_CR0_SEL_WRITE	0x065
+#define SVM_EXIT_IDTR_READ	0x066
+#define SVM_EXIT_GDTR_READ	0x067
+#define SVM_EXIT_LDTR_READ	0x068
+#define SVM_EXIT_TR_READ	0x069
+#define SVM_EXIT_IDTR_WRITE	0x06a
+#define SVM_EXIT_GDTR_WRITE	0x06b
+#define SVM_EXIT_LDTR_WRITE	0x06c
+#define SVM_EXIT_TR_WRITE	0x06d
+#define SVM_EXIT_RDTSC		0x06e
+#define SVM_EXIT_RDPMC		0x06f
+#define SVM_EXIT_PUSHF		0x070
+#define SVM_EXIT_POPF		0x071
+#define SVM_EXIT_CPUID		0x072
+#define SVM_EXIT_RSM		0x073
+#define SVM_EXIT_IRET		0x074
+#define SVM_EXIT_SWINT		0x075
+#define SVM_EXIT_INVD		0x076
+#define SVM_EXIT_PAUSE		0x077
+#define SVM_EXIT_HLT		0x078
+#define SVM_EXIT_INVLPG		0x079
+#define SVM_EXIT_INVLPGA	0x07a
+#define SVM_EXIT_IOIO		0x07b
+#define SVM_EXIT_MSR		0x07c
+#define SVM_EXIT_TASK_SWITCH	0x07d
+#define SVM_EXIT_FERR_FREEZE	0x07e
+#define SVM_EXIT_SHUTDOWN	0x07f
+#define SVM_EXIT_VMRUN		0x080
+#define SVM_EXIT_VMMCALL	0x081
+#define SVM_EXIT_VMLOAD		0x082
+#define SVM_EXIT_VMSAVE		0x083
+#define SVM_EXIT_STGI		0x084
+#define SVM_EXIT_CLGI		0x085
+#define SVM_EXIT_SKINIT		0x086
+#define SVM_EXIT_RDTSCP		0x087
+#define SVM_EXIT_ICEBP		0x088
+#define SVM_EXIT_WBINVD		0x089
+#define SVM_EXIT_NPF  		0x400
+
+#define SVM_EXIT_ERR		-1
+
+#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"
+#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb"
+#define SVM_CLGI   ".byte 0x0f, 0x01, 0xdd"
+#define SVM_STGI   ".byte 0x0f, 0x01, 0xdc"
+#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf"
+
+#endif
+

drivers/kvm/x86_emulate.h

+/******************************************************************************
+ * x86_emulate.h
+ *
+ * Generic x86 (32-bit and 64-bit) instruction decoder and emulator.
+ *
+ * Copyright (c) 2005 Keir Fraser
+ *
+ * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
+ */
+
+#ifndef __X86_EMULATE_H__
+#define __X86_EMULATE_H__
+
+struct x86_emulate_ctxt;
+
+/*
+ * x86_emulate_ops:
+ *
+ * These operations represent the instruction emulator's interface to memory.
+ * There are two categories of operation: those that act on ordinary memory
+ * regions (*_std), and those that act on memory regions known to require
+ * special treatment or emulation (*_emulated).
+ *
+ * The emulator assumes that an instruction accesses only one 'emulated memory'
+ * location, that this location is the given linear faulting address (cr2), and
+ * that this is one of the instruction's data operands. Instruction fetches and
+ * stack operations are assumed never to access emulated memory. The emulator
+ * automatically deduces which operand of a string-move operation is accessing
+ * emulated memory, and assumes that the other operand accesses normal memory.
+ *
+ * NOTES:
+ *  1. The emulator isn't very smart about emulated vs. standard memory.
+ *     'Emulated memory' access addresses should be checked for sanity.
+ *     'Normal memory' accesses may fault, and the caller must arrange to
+ *     detect and handle reentrancy into the emulator via recursive faults.
+ *     Accesses may be unaligned and may cross page boundaries.
+ *  2. If the access fails (cannot emulate, or a standard access faults) then
+ *     it is up to the memop to propagate the fault to the guest VM via
+ *     some out-of-band mechanism, unknown to the emulator. The memop signals
+ *     failure by returning X86EMUL_PROPAGATE_FAULT to the emulator, which will
+ *     then immediately bail.
+ *  3. Valid access sizes are 1, 2, 4 and 8 bytes. On x86/32 systems only
+ *     cmpxchg8b_emulated need support 8-byte accesses.
+ *  4. The emulator cannot handle 64-bit mode emulation on an x86/32 system.
+ */
+/* Access completed successfully: continue emulation as normal. */
+#define X86EMUL_CONTINUE        0
+/* Access is unhandleable: bail from emulation and return error to caller. */
+#define X86EMUL_UNHANDLEABLE    1
+/* Terminate emulation but return success to the caller. */
+#define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */
+#define X86EMUL_RETRY_INSTR     2 /* retry the instruction for some reason */
+#define X86EMUL_CMPXCHG_FAILED  2 /* cmpxchg did not see expected value */
+struct x86_emulate_ops {
+	/*
+	 * read_std: Read bytes of standard (non-emulated/special) memory.
+	 *           Used for instruction fetch, stack operations, and others.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_std)(unsigned long addr,
+			unsigned long *val,
+			unsigned int bytes, struct x86_emulate_ctxt * ctxt);
+
+	/*
+	 * 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,
+			 unsigned long val,
+			 unsigned int bytes, struct x86_emulate_ctxt * ctxt);
+
+	/*
+	 * read_emulated: Read bytes from emulated/special memory area.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_emulated) (unsigned long addr,
+			      unsigned long *val,
+			      unsigned int bytes,
+			      struct x86_emulate_ctxt * ctxt);
+
+	/*
+	 * write_emulated: Read bytes from emulated/special memory area.
+	 *  @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_emulated) (unsigned long addr,
+			       unsigned long val,
+			       unsigned int bytes,
+			       struct x86_emulate_ctxt * ctxt);
+
+	/*
+	 * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an
+	 *                   emulated/special memory area.
+	 *  @addr:  [IN ] Linear address to access.
+	 *  @old:   [IN ] Value expected to be current at @addr.
+	 *  @new:   [IN ] Value to write to @addr.
+	 *  @bytes: [IN ] Number of bytes to access using CMPXCHG.
+	 */
+	int (*cmpxchg_emulated) (unsigned long addr,
+				 unsigned long old,
+				 unsigned long new,
+				 unsigned int bytes,
+				 struct x86_emulate_ctxt * ctxt);
+
+	/*
+	 * cmpxchg8b_emulated: Emulate an atomic (LOCKed) CMPXCHG8B operation on an
+	 *                     emulated/special memory area.
+	 *  @addr:  [IN ] Linear address to access.
+	 *  @old:   [IN ] Value expected to be current at @addr.
+	 *  @new:   [IN ] Value to write to @addr.
+	 * NOTES:
+	 *  1. This function is only ever called when emulating a real CMPXCHG8B.
+	 *  2. This function is *never* called on x86/64 systems.
+	 *  2. Not defining this function (i.e., specifying NULL) is equivalent
+	 *     to defining a function that always returns X86EMUL_UNHANDLEABLE.
+	 */
+	int (*cmpxchg8b_emulated) (unsigned long addr,
+				   unsigned long old_lo,
+				   unsigned long old_hi,
+				   unsigned long new_lo,
+				   unsigned long new_hi,
+				   struct x86_emulate_ctxt * ctxt);
+};
+
+struct cpu_user_regs;
+
+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;
+
+	unsigned long cs_base;
+	unsigned long ds_base;
+	unsigned long es_base;
+	unsigned long ss_base;
+	unsigned long gs_base;
+	unsigned long fs_base;
+};
+
+/* Execution mode, passed to the emulator. */
+#define X86EMUL_MODE_REAL     0	/* Real mode.             */
+#define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
+#define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
+#define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
+
+/* Host execution mode. */
+#if defined(__i386__)
+#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
+#elif defined(__x86_64__)
+#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,
+		      struct x86_emulate_ops *ops);
+
+/*
+ * Given the 'reg' portion of a ModRM byte, and a register block, return a
+ * pointer into the block that addresses the relevant register.
+ * @highbyte_regs specifies whether to decode AH,CH,DH,BH.
+ */
+void *decode_register(u8 modrm_reg, unsigned long *regs,
+		      int highbyte_regs);
+
+#endif				/* __X86_EMULATE_H__ */

include/linux/kvm.h

+#ifndef __LINUX_KVM_H
+#define __LINUX_KVM_H
+
+/*
+ * Userspace interface for /dev/kvm - kernel based virtual machine
+ *
+ * Note: this interface is considered experimental and may change without
+ *       notice.
+ */
+
+#include <asm/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Architectural interrupt line count, and the size of the bitmap needed
+ * to hold them.
+ */
+#define KVM_NR_INTERRUPTS 256
+#define KVM_IRQ_BITMAP_SIZE_BYTES    ((KVM_NR_INTERRUPTS + 7) / 8)
+#define KVM_IRQ_BITMAP_SIZE(type)    (KVM_IRQ_BITMAP_SIZE_BYTES / sizeof(type))
+
+
+/* for KVM_CREATE_MEMORY_REGION */
+struct kvm_memory_region {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+};
+
+/* for kvm_memory_region::flags */
+#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+
+
+#define KVM_EXIT_TYPE_FAIL_ENTRY 1
+#define KVM_EXIT_TYPE_VM_EXIT    2
+
+enum kvm_exit_reason {
+	KVM_EXIT_UNKNOWN          = 0,
+	KVM_EXIT_EXCEPTION        = 1,
+	KVM_EXIT_IO               = 2,
+	KVM_EXIT_CPUID            = 3,
+	KVM_EXIT_DEBUG            = 4,
+	KVM_EXIT_HLT              = 5,
+	KVM_EXIT_MMIO             = 6,
+};
+
+/* for KVM_RUN */
+struct kvm_run {
+	/* in */
+	__u32 vcpu;
+	__u32 emulated;  /* skip current instruction */
+	__u32 mmio_completed; /* mmio request completed */
+
+	/* out */
+	__u32 exit_type;
+	__u32 exit_reason;
+	__u32 instruction_length;
+	union {
+		/* KVM_EXIT_UNKNOWN */
+		struct {
+			__u32 hardware_exit_reason;
+		} hw;
+		/* KVM_EXIT_EXCEPTION */
+		struct {
+			__u32 exception;
+			__u32 error_code;
+		} ex;
+		/* KVM_EXIT_IO */
+		struct {
+#define KVM_EXIT_IO_IN  0
+#define KVM_EXIT_IO_OUT 1
+			__u8 direction;
+			__u8 size; /* bytes */
+			__u8 string;
+			__u8 string_down;
+			__u8 rep;
+			__u8 pad;
+			__u16 port;
+			__u64 count;
+			union {
+				__u64 address;
+				__u32 value;
+			};
+		} io;
+		struct {
+		} debug;
+		/* KVM_EXIT_MMIO */
+		struct {
+			__u64 phys_addr;
+			__u8  data[8];
+			__u32 len;
+			__u8  is_write;
+		} mmio;
+	};
+};
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* in */
+	__u32 vcpu;
+	__u32 padding;
+
+	/* 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;
+};
+
+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 {
+	/* in */
+	__u32 vcpu;
+	__u32 padding;
+
+	/* 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_IRQ_BITMAP_SIZE(__u64)];
+};
+
+struct kvm_msr_entry {
+	__u32 index;
+	__u32 reserved;
+	__u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+	__u32 vcpu;
+	__u32 nmsrs; /* number of msrs in entries */
+
+	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 */
+	__u64 linear_address;
+	__u32 vcpu;
+	__u32 padding;
+
+	/* out */
+	__u64 physical_address;
+	__u8  valid;
+	__u8  writeable;
+	__u8  usermode;
+};
+
+/* for KVM_INTERRUPT */
+struct kvm_interrupt {
+	/* in */
+	__u32 vcpu;
+	__u32 irq;
+};
+
+struct kvm_breakpoint {
+	__u32 enabled;
+	__u32 padding;
+	__u64 address;
+};
+
+/* for KVM_DEBUG_GUEST */
+struct kvm_debug_guest {
+	/* int */
+	__u32 vcpu;
+	__u32 enabled;
+	struct kvm_breakpoint breakpoints[4];
+	__u32 singlestep;
+};
+
+/* for KVM_GET_DIRTY_LOG */
+struct kvm_dirty_log {
+	__u32 slot;
+	__u32 padding;
+	union {
+		void __user *dirty_bitmap; /* one bit per page */
+		__u64 padding;
+	};
+};
+
+#define KVMIO 0xAE
+
+#define KVM_RUN                   _IOWR(KVMIO, 2, struct kvm_run)
+#define KVM_GET_REGS              _IOWR(KVMIO, 3, struct kvm_regs)
+#define KVM_SET_REGS              _IOW(KVMIO, 4, struct kvm_regs)
+#define KVM_GET_SREGS             _IOWR(KVMIO, 5, struct kvm_sregs)
+#define KVM_SET_SREGS             _IOW(KVMIO, 6, struct kvm_sregs)
+#define KVM_TRANSLATE             _IOWR(KVMIO, 7, struct kvm_translation)
+#define KVM_INTERRUPT             _IOW(KVMIO, 8, struct kvm_interrupt)
+#define KVM_DEBUG_GUEST           _IOW(KVMIO, 9, struct kvm_debug_guest)
+#define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 10, struct kvm_memory_region)
+#define KVM_CREATE_VCPU           _IOW(KVMIO, 11, int /* vcpu_slot */)
+#define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 12, struct kvm_dirty_log)
+#define KVM_GET_MSRS              _IOWR(KVMIO, 13, struct kvm_msrs)
+#define KVM_SET_MSRS              _IOWR(KVMIO, 14, struct kvm_msrs)
+#define KVM_GET_MSR_INDEX_LIST    _IOWR(KVMIO, 15, struct kvm_msr_list)
+
+#endif