xen.h

xen虚拟机源代码安装包

/******************************************************************************
 * xen.h
 * 
 * Guest OS interface to Xen.
 * 
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to
 * deal in the Software without restriction, including without limitation the
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
 * DEALINGS IN THE SOFTWARE.
 *
 * Copyright (c) 2004, K A Fraser
 */

#ifndef __XEN_PUBLIC_XEN_H__
#define __XEN_PUBLIC_XEN_H__

#include "xen-compat.h"

#if defined(__i386__) || defined(__x86_64__)
#include "arch-x86/xen.h"
#elif defined(__ia64__)
#include "arch-ia64.h"
#else
#error "Unsupported architecture"
#endif

#ifndef __ASSEMBLY__
/* Guest handles for primitive C types. */
DEFINE_XEN_GUEST_HANDLE(char);
__DEFINE_XEN_GUEST_HANDLE(uchar, unsigned char);
DEFINE_XEN_GUEST_HANDLE(int);
__DEFINE_XEN_GUEST_HANDLE(uint,  unsigned int);
DEFINE_XEN_GUEST_HANDLE(long);
__DEFINE_XEN_GUEST_HANDLE(ulong, unsigned long);
DEFINE_XEN_GUEST_HANDLE(void);

DEFINE_XEN_GUEST_HANDLE(xen_pfn_t);
#endif

/*
 * HYPERCALLS
 */

#define __HYPERVISOR_set_trap_table        0
#define __HYPERVISOR_mmu_update            1
#define __HYPERVISOR_set_gdt               2
#define __HYPERVISOR_stack_switch          3
#define __HYPERVISOR_set_callbacks         4
#define __HYPERVISOR_fpu_taskswitch        5
#define __HYPERVISOR_sched_op_compat       6 /* compat since 0x00030101 */
#define __HYPERVISOR_platform_op           7
#define __HYPERVISOR_set_debugreg          8
#define __HYPERVISOR_get_debugreg          9
#define __HYPERVISOR_update_descriptor    10
#define __HYPERVISOR_memory_op            12
#define __HYPERVISOR_multicall            13
#define __HYPERVISOR_update_va_mapping    14
#define __HYPERVISOR_set_timer_op         15
#define __HYPERVISOR_event_channel_op_compat 16 /* compat since 0x00030202 */
#define __HYPERVISOR_xen_version          17
#define __HYPERVISOR_console_io           18
#define __HYPERVISOR_physdev_op_compat    19 /* compat since 0x00030202 */
#define __HYPERVISOR_grant_table_op       20
#define __HYPERVISOR_vm_assist            21
#define __HYPERVISOR_update_va_mapping_otherdomain 22
#define __HYPERVISOR_iret                 23 /* x86 only */
#define __HYPERVISOR_vcpu_op              24
#define __HYPERVISOR_set_segment_base     25 /* x86/64 only */
#define __HYPERVISOR_mmuext_op            26
#define __HYPERVISOR_xsm_op               27
#define __HYPERVISOR_nmi_op               28
#define __HYPERVISOR_sched_op             29
#define __HYPERVISOR_callback_op          30
#define __HYPERVISOR_xenoprof_op          31
#define __HYPERVISOR_event_channel_op     32
#define __HYPERVISOR_physdev_op           33
#define __HYPERVISOR_hvm_op               34
#define __HYPERVISOR_sysctl               35
#define __HYPERVISOR_domctl               36
#define __HYPERVISOR_kexec_op             37

/* Architecture-specific hypercall definitions. */
#define __HYPERVISOR_arch_0               48
#define __HYPERVISOR_arch_1               49
#define __HYPERVISOR_arch_2               50
#define __HYPERVISOR_arch_3               51
#define __HYPERVISOR_arch_4               52
#define __HYPERVISOR_arch_5               53
#define __HYPERVISOR_arch_6               54
#define __HYPERVISOR_arch_7               55

/*
 * HYPERCALL COMPATIBILITY.
 */

/* New sched_op hypercall introduced in 0x00030101. */
#if __XEN_INTERFACE_VERSION__ < 0x00030101
#undef __HYPERVISOR_sched_op
#define __HYPERVISOR_sched_op __HYPERVISOR_sched_op_compat
#endif

/* New event-channel and physdev hypercalls introduced in 0x00030202. */
#if __XEN_INTERFACE_VERSION__ < 0x00030202
#undef __HYPERVISOR_event_channel_op
#define __HYPERVISOR_event_channel_op __HYPERVISOR_event_channel_op_compat
#undef __HYPERVISOR_physdev_op
#define __HYPERVISOR_physdev_op __HYPERVISOR_physdev_op_compat
#endif

/* New platform_op hypercall introduced in 0x00030204. */
#if __XEN_INTERFACE_VERSION__ < 0x00030204
#define __HYPERVISOR_dom0_op __HYPERVISOR_platform_op
#endif

/* 
 * VIRTUAL INTERRUPTS
 * 
 * Virtual interrupts that a guest OS may receive from Xen.
 * 
 * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
 * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
 * The latter can be allocated only once per guest: they must initially be
 * allocated to VCPU0 but can subsequently be re-bound.
 */
#define VIRQ_TIMER      0  /* V. Timebase update, and/or requested timeout.  */
#define VIRQ_DEBUG      1  /* V. Request guest to dump debug info.           */
#define VIRQ_CONSOLE    2  /* G. (DOM0) Bytes received on emergency console. */
#define VIRQ_DOM_EXC    3  /* G. (DOM0) Exceptional event for some domain.   */
#define VIRQ_TBUF       4  /* G. (DOM0) Trace buffer has records available.  */
#define VIRQ_DEBUGGER   6  /* G. (DOM0) A domain has paused for debugging.   */
#define VIRQ_XENOPROF   7  /* V. XenOprofile interrupt: new sample available */
#define VIRQ_CON_RING   8  /* G. (DOM0) Bytes received on console            */

/* Architecture-specific VIRQ definitions. */
#define VIRQ_ARCH_0    16
#define VIRQ_ARCH_1    17
#define VIRQ_ARCH_2    18
#define VIRQ_ARCH_3    19
#define VIRQ_ARCH_4    20
#define VIRQ_ARCH_5    21
#define VIRQ_ARCH_6    22
#define VIRQ_ARCH_7    23

#define NR_VIRQS       24

/*
 * MMU-UPDATE REQUESTS
 * 
 * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs.
 * A foreigndom (FD) can be specified (or DOMID_SELF for none).
 * Where the FD has some effect, it is described below.
 * ptr[1:0] specifies the appropriate MMU_* command.
 * 
 * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
 * Updates an entry in a page table. If updating an L1 table, and the new
 * table entry is valid/present, the mapped frame must belong to the FD, if
 * an FD has been specified. If attempting to map an I/O page then the
 * caller assumes the privilege of the FD.
 * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
 * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
 * ptr[:2]  -- Machine address of the page-table entry to modify.
 * val      -- Value to write.
 * 
 * ptr[1:0] == MMU_MACHPHYS_UPDATE:
 * Updates an entry in the machine->pseudo-physical mapping table.
 * ptr[:2]  -- Machine address within the frame whose mapping to modify.
 *             The frame must belong to the FD, if one is specified.
 * val      -- Value to write into the mapping entry.
 * 
 * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
 * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
 * with those in @val.
 */
#define MMU_NORMAL_PT_UPDATE      0 /* checked '*ptr = val'. ptr is MA.      */
#define MMU_MACHPHYS_UPDATE       1 /* ptr = MA of frame to modify entry for */
#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */

/*
 * MMU EXTENDED OPERATIONS
 * 
 * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
 * A foreigndom (FD) can be specified (or DOMID_SELF for none).
 * Where the FD has some effect, it is described below.
 * 
 * cmd: MMUEXT_(UN)PIN_*_TABLE
 * mfn: Machine frame number to be (un)pinned as a p.t. page.
 *      The frame must belong to the FD, if one is specified.
 * 
 * cmd: MMUEXT_NEW_BASEPTR
 * mfn: Machine frame number of new page-table base to install in MMU.
 * 
 * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only]
 * mfn: Machine frame number of new page-table base to install in MMU
 *      when in user space.
 * 
 * cmd: MMUEXT_TLB_FLUSH_LOCAL
 * No additional arguments. Flushes local TLB.
 * 
 * cmd: MMUEXT_INVLPG_LOCAL
 * linear_addr: Linear address to be flushed from the local TLB.
 * 
 * cmd: MMUEXT_TLB_FLUSH_MULTI
 * vcpumask: Pointer to bitmap of VCPUs to be flushed.
 * 
 * cmd: MMUEXT_INVLPG_MULTI
 * linear_addr: Linear address to be flushed.
 * vcpumask: Pointer to bitmap of VCPUs to be flushed.
 * 
 * cmd: MMUEXT_TLB_FLUSH_ALL
 * No additional arguments. Flushes all VCPUs' TLBs.
 * 
 * cmd: MMUEXT_INVLPG_ALL
 * linear_addr: Linear address to be flushed from all VCPUs' TLBs.
 * 
 * cmd: MMUEXT_FLUSH_CACHE
 * No additional arguments. Writes back and flushes cache contents.
 * 
 * cmd: MMUEXT_SET_LDT
 * linear_addr: Linear address of LDT base (NB. must be page-aligned).
 * nr_ents: Number of entries in LDT.
 */
#define MMUEXT_PIN_L1_TABLE      0
#define MMUEXT_PIN_L2_TABLE      1
#define MMUEXT_PIN_L3_TABLE      2
#define MMUEXT_PIN_L4_TABLE      3
#define MMUEXT_UNPIN_TABLE       4
#define MMUEXT_NEW_BASEPTR       5
#define MMUEXT_TLB_FLUSH_LOCAL   6
#define MMUEXT_INVLPG_LOCAL      7
#define MMUEXT_TLB_FLUSH_MULTI   8
#define MMUEXT_INVLPG_MULTI      9
#define MMUEXT_TLB_FLUSH_ALL    10
#define MMUEXT_INVLPG_ALL       11
#define MMUEXT_FLUSH_CACHE      12
#define MMUEXT_SET_LDT          13
#define MMUEXT_NEW_USER_BASEPTR 15

#ifndef __ASSEMBLY__
struct mmuext_op {
    unsigned int cmd;
    union {
        /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */
        xen_pfn_t     mfn;
        /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
        unsigned long linear_addr;
    } arg1;
    union {
        /* SET_LDT */
        unsigned int nr_ents;
        /* TLB_FLUSH_MULTI, INVLPG_MULTI */
#if __XEN_INTERFACE_VERSION__ >= 0x00030205
        XEN_GUEST_HANDLE(void) vcpumask;
#else
        void *vcpumask;
#endif
    } arg2;
};
typedef struct mmuext_op mmuext_op_t;
DEFINE_XEN_GUEST_HANDLE(mmuext_op_t);
#endif

/* These are passed as 'flags' to update_va_mapping. They can be ORed. */
/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap.   */
/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer.         */
#define UVMF_NONE               (0UL<<0) /* No flushing at all.   */
#define UVMF_TLB_FLUSH          (1UL<<0) /* Flush entire TLB(s).  */
#define UVMF_INVLPG             (2UL<<0) /* Flush only one entry. */
#define UVMF_FLUSHTYPE_MASK     (3UL<<0)
#define UVMF_MULTI              (0UL<<2) /* Flush subset of TLBs. */
#define UVMF_LOCAL              (0UL<<2) /* Flush local TLB.      */
#define UVMF_ALL                (1UL<<2) /* Flush all TLBs.       */

/*
 * Commands to HYPERVISOR_console_io().
 */
#define CONSOLEIO_write         0
#define CONSOLEIO_read          1

/*
 * Commands to HYPERVISOR_vm_assist().
 */
#define VMASST_CMD_enable                0
#define VMASST_CMD_disable               1

/* x86/32 guests: simulate full 4GB segment limits. */
#define VMASST_TYPE_4gb_segments         0

/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
#define VMASST_TYPE_4gb_segments_notify  1

/*
 * x86 guests: support writes to bottom-level PTEs.
 * NB1. Page-directory entries cannot be written.
 * NB2. Guest must continue to remove all writable mappings of PTEs.
 */
#define VMASST_TYPE_writable_pagetables  2

/* x86/PAE guests: support PDPTs above 4GB. */
#define VMASST_TYPE_pae_extended_cr3     3

#define MAX_VMASST_TYPE                  3

#ifndef __ASSEMBLY__

typedef uint16_t domid_t;

/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */