xen.h revision ad09f8b827db90c9a0093f0b6382803fa64a5fd1
/******************************************************************************
* 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
* 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"
#define __i386__ /* foo */
#endif
#if defined(__amd64) && !defined(__x86_64__)
#define __x86_64__
#endif
#if defined(_ASM) && !defined(__ASSEMBLY__)
#define __ASSEMBLY__
#endif
#if defined(__i386__) || defined(__x86_64__)
#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);
#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_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_xen_version 17
#define __HYPERVISOR_console_io 18
#define __HYPERVISOR_grant_table_op 20
#define __HYPERVISOR_vm_assist 21
#define __HYPERVISOR_update_va_mapping_otherdomain 22
#define __HYPERVISOR_vcpu_op 24
#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
#endif
/* New event-channel and physdev hypercalls introduced in 0x00030202. */
#if __XEN_INTERFACE_VERSION__ < 0x00030202
#endif
/* New platform_op hypercall introduced in 0x00030204. */
#if __XEN_INTERFACE_VERSION__ < 0x00030204
#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. */
/* 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
* 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. */
/*
* 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.
*
* cmd: MMUEXT_CLEAR_PAGE
* mfn: Machine frame number to be cleared.
*
* cmd: MMUEXT_COPY_PAGE
* mfn: Machine frame number of the destination page.
* src_mfn: Machine frame number of the source page.
*/
#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
#define MMUEXT_CLEAR_PAGE 16
#define MMUEXT_COPY_PAGE 17
#ifndef __ASSEMBLY__
struct mmuext_op {
unsigned int cmd;
union {
/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
* CLEAR_PAGE, COPY_PAGE */
/* 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
#else
const void *vcpumask;
#endif
/* COPY_PAGE */
} arg2;
};
typedef struct mmuext_op 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_FLUSHTYPE_MASK (3UL<<0)
/*
* Commands to HYPERVISOR_console_io().
*/
#define CONSOLEIO_write 0
#define CONSOLEIO_read 1
#define CONSOLEIO_get_device 32
/*
* 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
#define VMASST_TYPE_pae_extended_cr3 3
#define MAX_VMASST_TYPE 3
#ifndef __ASSEMBLY__
/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
#define DOMID_FIRST_RESERVED (0x7FF0U)
/* DOMID_SELF is used in certain contexts to refer to oneself. */
#define DOMID_SELF (0x7FF0U)
/*
* DOMID_IO is used to restrict page-table updates to mapping I/O memory.
* Although no Foreign Domain need be specified to map I/O pages, DOMID_IO
* is useful to ensure that no mappings to the OS's own heap are accidentally
* installed. (e.g., in Linux this could cause havoc as reference counts
* This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
* be specified by any calling domain.
*/
#define DOMID_IO (0x7FF1U)
/*
* DOMID_XEN is used to allow privileged domains to map restricted parts of
* Xen's heap space (e.g., the machine_to_phys table).
* This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
* the caller is privileged.
*/
#define DOMID_XEN (0x7FF2U)
/* DOMID_INVALID is used to identity invalid domid */
#define DOMID_INVALID (0x7FFFU)
/*
* Send an array of these to HYPERVISOR_mmu_update().
*/
struct mmu_update {
};
typedef struct mmu_update mmu_update_t;
/*
* Send an array of these to HYPERVISOR_multicall().
* NB. The fields are natural register size for this architecture.
*/
struct multicall_entry {
unsigned long args[6];
};
typedef struct multicall_entry multicall_entry_t;
/*
* Event channel endpoints per domain:
* 1024 if a long is 32 bits; 4096 if a long is 64 bits.
*/
#define NR_EVENT_CHANNELS (sizeof(unsigned long) * sizeof(unsigned long) * 64)
struct vcpu_time_info {
/*
* Updates to the following values are preceded and followed by an
* increment of 'version'. The guest can therefore detect updates by
* looking for changes to 'version'. If the least-significant bit of
* the version number is set then an update is in progress and the guest
* must wait to read a consistent set of values.
* The correct way to interact with the version number is similar to
* Linux's seqlock: see the implementations of read_seqbegin/read_seqretry.
*/
/*
* Current system time:
* system_time +
* ((((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul) >> 32)
* CPU frequency (Hz):
* ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift
*/
}; /* 32 bytes */
typedef struct vcpu_time_info vcpu_time_info_t;
struct vcpu_info {
/*
* 'evtchn_upcall_pending' is written non-zero by Xen to indicate
* a pending notification for a particular VCPU. It is then cleared
* by the guest OS /before/ checking for pending work, thus avoiding
* a set-and-check race. Note that the mask is only accessed by Xen
* on the CPU that is currently hosting the VCPU. This means that the
* pending and mask flags can be updated by the guest without special
* synchronisation (i.e., no need for the x86 LOCK prefix).
* This may seem suboptimal because if the pending flag is set by
* a different CPU then an IPI may be scheduled even when the mask
* is set. However, note:
* 1. The task of 'interrupt holdoff' is covered by the per-event-
* channel mask bits. A 'noisy' event that is continually being
* triggered can be masked at source at this very precise
* granularity.
* 2. The main purpose of the per-VCPU mask is therefore to restrict
* reentrant execution: whether for concurrency control, or to
* prevent unbounded stack usage. Whatever the purpose, we expect
* that the mask will be asserted only for short periods at a time,
* and so the likelihood of a 'spurious' IPI is suitably small.
* The mask is read before making an event upcall to the guest: a
* non-zero mask therefore guarantees that the VCPU will not receive
* an upcall activation. The mask is cleared when the VCPU requests
* to block: this avoids wakeup-waiting races.
*/
unsigned long evtchn_pending_sel;
struct arch_vcpu_info arch;
struct vcpu_time_info time;
}; /* 64 bytes (x86) */
#ifndef __XEN__
typedef struct vcpu_info vcpu_info_t;
#endif
/*
*
* This structure is defined to be both smaller than a page, and the
* only data on the shared page, but may vary in actual size even within
* compatible Xen versions; guests should not rely on the size
* of this structure remaining constant.
*/
struct shared_info {
/*
* A domain can create "event channels" on which it can send and receive
* asynchronous event notifications. There are three classes of event that
* are delivered by this mechanism:
* 1. Bi-directional inter- and intra-domain connections. Domains must
* arrange out-of-band to set up a connection (usually by allocating
* an unbound 'listener' port and avertising that via a storage service
* such as xenstore).
* 2. Physical interrupts. A domain with suitable hardware-access
* privileges can bind an event-channel port to a physical interrupt
* source.
* 3. Virtual interrupts ('events'). A domain can bind an event-channel
* port to a virtual interrupt source, such as the virtual-timer
* device or the emergency console.
*
* Event channels are addressed by a "port index". Each channel is
* associated with two bits of information:
* 1. PENDING -- notifies the domain that there is a pending notification
* to be processed. This bit is cleared by the guest.
* 2. MASK -- if this bit is clear then a 0->1 transition of PENDING
* will cause an asynchronous upcall to be scheduled. This bit is only
* updated by the guest. It is read-only within Xen. If a channel
* becomes pending while the channel is masked then the 'edge' is lost
* (i.e., when the channel is unmasked, the guest must manually handle
* pending notifications as no upcall will be scheduled by Xen).
*
* To expedite scanning of pending notifications, any 0->1 pending
* transition on an unmasked channel causes a corresponding bit in a
* per-vcpu selector word to be set. Each bit in the selector covers a
* 'C long' in the PENDING bitfield array.
*/
unsigned long evtchn_pending[sizeof(unsigned long) * 8];
unsigned long evtchn_mask[sizeof(unsigned long) * 8];
/*
* Wallclock time: updated only by control software. Guests should base
* their gettimeofday() syscall on this wallclock-base value.
*/
struct arch_shared_info arch;
};
#ifndef __XEN__
typedef struct shared_info shared_info_t;
#endif
/*
* Start-of-day memory layout:
* 1. The domain is started within contiguous virtual-memory region.
* 2. The contiguous region ends on an aligned 4MB boundary.
* 3. This the order of bootstrap elements in the initial virtual region:
* a. relocated kernel image
* b. initial ram disk [mod_start, mod_len]
* c. list of allocated page frames [mfn_list, nr_pages]
* (unless relocated due to XEN_ELFNOTE_INIT_P2M)
* d. start_info_t structure [register ESI (x86)]
* e. bootstrap page tables [pt_base, CR3 (x86)]
* f. bootstrap stack [register ESP (x86)]
* 4. Bootstrap elements are packed together, but each is 4kB-aligned.
* 5. The initial ram disk may be omitted.
* 6. The list of page frames forms a contiguous 'pseudo-physical' memory
* layout for the domain. In particular, the bootstrap virtual-memory
* region is a 1:1 mapping to the first section of the pseudo-physical map.
* 7. All bootstrap elements are mapped read-writable for the guest OS. The
* only exception is the bootstrap page table, which is mapped read-only.
* 8. There is guaranteed to be at least 512kB padding after the final
* bootstrap element. If necessary, the bootstrap virtual region is
* extended by an extra 4MB to ensure this.
*/
#define MAX_GUEST_CMDLINE 1024
struct start_info {
/* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */
unsigned long nr_pages; /* Total pages allocated to this domain. */
unsigned long shared_info; /* MACHINE address of shared info struct. */
union {
struct {
} domU;
struct {
} dom0;
} console;
/* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */
unsigned long pt_base; /* VIRTUAL address of page directory. */
unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */
unsigned long mfn_list; /* VIRTUAL address of page-frame list. */
unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */
unsigned long mod_len; /* Size (bytes) of pre-loaded module. */
/* The pfn range here covers both page table and p->m table frames. */
unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */
unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */
};
typedef struct start_info start_info_t;
/* New console union for dom0 introduced in 0x00030203. */
#if __XEN_INTERFACE_VERSION__ < 0x00030203
#endif
/* These flags are passed in the 'flags' field of start_info_t. */
#define XEN_CONSOLE_INVALID -1
#define XEN_CONSOLE_COM1 0
#define XEN_CONSOLE_COM2 1
#define XEN_CONSOLE_VGA 2
typedef struct dom0_vga_console_info {
#define XEN_VGATYPE_TEXT_MODE_3 0x03
#define XEN_VGATYPE_VESA_LFB 0x23
union {
struct {
/* Font height, in pixels. */
/* Cursor location (column, row). */
/* Number of rows and columns (dimensions in characters). */
} text_mode_3;
struct {
/* Width and height, in pixels. */
/* Bytes per scan line. */
/* Bits per pixel. */
/* LFB physical address, and size (in units of 64kB). */
/* RGB mask offsets and sizes, as defined by VBE 1.2+ */
#if __XEN_INTERFACE_VERSION__ >= 0x00030206
/* VESA capabilities (offset 0xa, VESA command 0x4f00). */
/* Mode attributes (offset 0x0, VESA command 0x4f01). */
#endif
} vesa_lfb;
} u;
/* Turn a plain number into a C unsigned long constant. */
#define __mk_unsigned_long(x) x ## UL
#define mk_unsigned_long(x) __mk_unsigned_long(x)
#else /* __ASSEMBLY__ */
/* In assembly code we cannot use C numeric constant suffixes. */
#define mk_unsigned_long(x) x
#endif /* !__ASSEMBLY__ */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#ifndef uint64_aligned_t
#define uint64_aligned_t uint64_t
#endif
#ifndef XEN_GUEST_HANDLE_64
#endif
#endif
#endif /* __XEN_PUBLIC_XEN_H__ */
/*
* Local variables:
* mode: C
* c-set-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/