summaryrefslogtreecommitdiff
path: root/xen/public/xen.h
blob: 084bb90aa876f6e59e65b59a550d9666d147007f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
/******************************************************************************
 * 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 <sys/types.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.
 *
 * 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 */
        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
        /* COPY_PAGE */
        xen_pfn_t src_mfn;
    } 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. */
#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
 * aren't adjusted on the I/O-mapping code path).
 * 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)

/*
 * Send an array of these to HYPERVISOR_mmu_update().
 * NB. The fields are natural pointer/address size for this architecture.
 */
struct mmu_update {
    uint64_t ptr;       /* Machine address of PTE. */
    uint64_t val;       /* New contents of PTE.    */
};
typedef struct mmu_update mmu_update_t;
DEFINE_XEN_GUEST_HANDLE(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 op, result;
    unsigned long args[6];
};
typedef struct multicall_entry multicall_entry_t;
DEFINE_XEN_GUEST_HANDLE(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.
     */
    uint32_t version;
    uint32_t pad0;
    uint64_t tsc_timestamp;   /* TSC at last update of time vals.  */
    uint64_t system_time;     /* Time, in nanosecs, since boot.    */
    /*
     * 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
     */
    uint32_t tsc_to_system_mul;
    int8_t   tsc_shift;
    int8_t   pad1[3];
}; /* 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.
     */
    uint8_t evtchn_upcall_pending;
    uint8_t evtchn_upcall_mask;
    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

/*
 * Xen/kernel shared data -- pointer provided in start_info.
 *
 * 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 {
    struct vcpu_info vcpu_info[MAX_VIRT_CPUS];

    /*
     * 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.
     */
    uint32_t wc_version;      /* Version counter: see vcpu_time_info_t. */
    uint32_t wc_sec;          /* Secs  00:00:00 UTC, Jan 1, 1970.  */
    uint32_t wc_nsec;         /* Nsecs 00:00:00 UTC, Jan 1, 1970.  */

    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]
 *      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.    */
    char magic[32];             /* "xen-<version>-<platform>".            */
    unsigned long nr_pages;     /* Total pages allocated to this domain.  */
    unsigned long shared_info;  /* MACHINE address of shared info struct. */
    uint32_t flags;             /* SIF_xxx flags.                         */
    xen_pfn_t store_mfn;        /* MACHINE page number of shared page.    */
    uint32_t store_evtchn;      /* Event channel for store communication. */
    union {
        struct {
            xen_pfn_t mfn;      /* MACHINE page number of console page.   */
            uint32_t  evtchn;   /* Event channel for console page.        */
        } domU;
        struct {
            uint32_t info_off;  /* Offset of console_info struct.         */
            uint32_t info_size; /* Size of console_info struct from start.*/
        } 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.     */
    int8_t cmd_line[MAX_GUEST_CMDLINE];

	/* hackish, for multiboot compatibility */
	unsigned		mods_count;
};
typedef struct start_info start_info_t;

/* New console union for dom0 introduced in 0x00030203. */
#if __XEN_INTERFACE_VERSION__ < 0x00030203
#define console_mfn    console.domU.mfn
#define console_evtchn console.domU.evtchn
#endif

/* These flags are passed in the 'flags' field of start_info_t. */
#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
#define SIF_MULTIBOOT_MOD (1<<2)  /* Is this the initial control domain? */
#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */

typedef struct dom0_vga_console_info {
    uint8_t video_type; /* DOM0_VGA_CONSOLE_??? */
#define XEN_VGATYPE_TEXT_MODE_3 0x03
#define XEN_VGATYPE_VESA_LFB    0x23

    union {
        struct {
            /* Font height, in pixels. */
            uint16_t font_height;
            /* Cursor location (column, row). */
            uint16_t cursor_x, cursor_y;
            /* Number of rows and columns (dimensions in characters). */
            uint16_t rows, columns;
        } text_mode_3;

        struct {
            /* Width and height, in pixels. */
            uint16_t width, height;
            /* Bytes per scan line. */
            uint16_t bytes_per_line;
            /* Bits per pixel. */
            uint16_t bits_per_pixel;
            /* LFB physical address, and size (in units of 64kB). */
            uint32_t lfb_base;
            uint32_t lfb_size;
            /* RGB mask offsets and sizes, as defined by VBE 1.2+ */
            uint8_t  red_pos, red_size;
            uint8_t  green_pos, green_size;
            uint8_t  blue_pos, blue_size;
            uint8_t  rsvd_pos, rsvd_size;
#if __XEN_INTERFACE_VERSION__ >= 0x00030206
            /* VESA capabilities (offset 0xa, VESA command 0x4f00). */
            uint32_t gbl_caps;
            /* Mode attributes (offset 0x0, VESA command 0x4f01). */
            uint16_t mode_attrs;
#endif
        } vesa_lfb;
    } u;
} dom0_vga_console_info_t;
#define xen_vga_console_info dom0_vga_console_info
#define xen_vga_console_info_t dom0_vga_console_info_t

typedef uint8_t xen_domain_handle_t[16];

/* 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)

__DEFINE_XEN_GUEST_HANDLE(uint8,  uint8_t);
__DEFINE_XEN_GUEST_HANDLE(uint16, uint16_t);
__DEFINE_XEN_GUEST_HANDLE(uint32, uint32_t);
__DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t);

#else /* __ASSEMBLY__ */

/* In assembly code we cannot use C numeric constant suffixes. */
#define mk_unsigned_long(x) x

#endif /* !__ASSEMBLY__ */

/* Default definitions for macros used by domctl/sysctl. */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#ifndef uint64_aligned_t
#define uint64_aligned_t uint64_t
#endif
#ifndef XEN_GUEST_HANDLE_64
#define XEN_GUEST_HANDLE_64(name) XEN_GUEST_HANDLE(name)
#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:
 */