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
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
|
#ifndef __SCHED_H__
#define __SCHED_H__
#include <xen/types.h>
#include <xen/spinlock.h>
#include <xen/shared.h>
#include <xen/timer.h>
#include <xen/rangeset.h>
#include <xen/domain.h>
#include <xen/rcupdate.h>
#include <xen/cpumask.h>
#include <xen/nodemask.h>
#include <xen/radix-tree.h>
#include <xen/multicall.h>
#include <xen/tasklet.h>
#include <xen/mm.h>
#include <xen/smp.h>
#include <xen/perfc.h>
#include <asm/atomic.h>
#include <xen/wait.h>
#include <public/xen.h>
#include <public/domctl.h>
#include <public/sysctl.h>
#include <public/vcpu.h>
#include <public/mem_event.h>
#ifdef CONFIG_COMPAT
#include <compat/vcpu.h>
DEFINE_XEN_GUEST_HANDLE(vcpu_runstate_info_compat_t);
#endif
/*
* Stats
*
* Enable and ease the use of scheduling related performance counters.
*
*/
#ifdef PERF_COUNTERS
#define SCHED_STATS
#endif
#define SCHED_STAT_CRANK(_X) (perfc_incr(_X))
/* A global pointer to the initial domain (DOM0). */
extern struct domain *dom0;
#ifndef CONFIG_COMPAT
#define BITS_PER_EVTCHN_WORD(d) BITS_PER_XEN_ULONG
#else
#define BITS_PER_EVTCHN_WORD(d) (has_32bit_shinfo(d) ? 32 : BITS_PER_XEN_ULONG)
#endif
#define MAX_EVTCHNS(d) (BITS_PER_EVTCHN_WORD(d) * BITS_PER_EVTCHN_WORD(d))
#define EVTCHNS_PER_BUCKET 128
#define NR_EVTCHN_BUCKETS (NR_EVENT_CHANNELS / EVTCHNS_PER_BUCKET)
struct evtchn
{
#define ECS_FREE 0 /* Channel is available for use. */
#define ECS_RESERVED 1 /* Channel is reserved. */
#define ECS_UNBOUND 2 /* Channel is waiting to bind to a remote domain. */
#define ECS_INTERDOMAIN 3 /* Channel is bound to another domain. */
#define ECS_PIRQ 4 /* Channel is bound to a physical IRQ line. */
#define ECS_VIRQ 5 /* Channel is bound to a virtual IRQ line. */
#define ECS_IPI 6 /* Channel is bound to a virtual IPI line. */
u8 state; /* ECS_* */
u8 xen_consumer; /* Consumer in Xen, if any? (0 = send to guest) */
u16 notify_vcpu_id; /* VCPU for local delivery notification */
union {
struct {
domid_t remote_domid;
} unbound; /* state == ECS_UNBOUND */
struct {
u16 remote_port;
struct domain *remote_dom;
} interdomain; /* state == ECS_INTERDOMAIN */
struct {
u16 irq;
u16 next_port;
u16 prev_port;
} pirq; /* state == ECS_PIRQ */
u16 virq; /* state == ECS_VIRQ */
} u;
#ifdef FLASK_ENABLE
void *ssid;
#endif
};
int evtchn_init(struct domain *d); /* from domain_create */
void evtchn_destroy(struct domain *d); /* from domain_kill */
void evtchn_destroy_final(struct domain *d); /* from complete_domain_destroy */
struct waitqueue_vcpu;
struct vcpu
{
int vcpu_id;
int processor;
vcpu_info_t *vcpu_info;
struct domain *domain;
struct vcpu *next_in_list;
s_time_t periodic_period;
s_time_t periodic_last_event;
struct timer periodic_timer;
struct timer singleshot_timer;
struct timer poll_timer; /* timeout for SCHEDOP_poll */
void *sched_priv; /* scheduler-specific data */
struct vcpu_runstate_info runstate;
#ifndef CONFIG_COMPAT
# define runstate_guest(v) ((v)->runstate_guest)
XEN_GUEST_HANDLE(vcpu_runstate_info_t) runstate_guest; /* guest address */
#else
# define runstate_guest(v) ((v)->runstate_guest.native)
union {
XEN_GUEST_HANDLE(vcpu_runstate_info_t) native;
XEN_GUEST_HANDLE(vcpu_runstate_info_compat_t) compat;
} runstate_guest; /* guest address */
#endif
/* last time when vCPU is scheduled out */
uint64_t last_run_time;
/* Has the FPU been initialised? */
bool_t fpu_initialised;
/* Has the FPU been used since it was last saved? */
bool_t fpu_dirtied;
/* Initialization completed for this VCPU? */
bool_t is_initialised;
/* Currently running on a CPU? */
bool_t is_running;
/* VCPU should wake fast (do not deep sleep the CPU). */
bool_t is_urgent;
#ifdef VCPU_TRAP_LAST
#define VCPU_TRAP_NONE 0
struct {
bool_t pending;
uint8_t old_mask;
} async_exception_state[VCPU_TRAP_LAST];
#define async_exception_state(t) async_exception_state[(t)-1]
uint8_t async_exception_mask;
#endif
/* Require shutdown to be deferred for some asynchronous operation? */
bool_t defer_shutdown;
/* VCPU is paused following shutdown request (d->is_shutting_down)? */
bool_t paused_for_shutdown;
/* VCPU need affinity restored */
bool_t affinity_broken;
/*
* > 0: a single port is being polled;
* = 0: nothing is being polled (vcpu should be clear in d->poll_mask);
* < 0: multiple ports may be being polled.
*/
int poll_evtchn;
/* (over-)protected by ->domain->event_lock */
int pirq_evtchn_head;
unsigned long pause_flags;
atomic_t pause_count;
/* IRQ-safe virq_lock protects against delivering VIRQ to stale evtchn. */
u16 virq_to_evtchn[NR_VIRQS];
spinlock_t virq_lock;
/* Bitmask of CPUs on which this VCPU may run. */
cpumask_var_t cpu_affinity;
/* Used to change affinity temporarily. */
cpumask_var_t cpu_affinity_tmp;
/* Used to restore affinity across S3. */
cpumask_var_t cpu_affinity_saved;
/* Bitmask of CPUs which are holding onto this VCPU's state. */
cpumask_var_t vcpu_dirty_cpumask;
/* Tasklet for continue_hypercall_on_cpu(). */
struct tasklet continue_hypercall_tasklet;
/* Multicall information. */
struct mc_state mc_state;
struct waitqueue_vcpu *waitqueue_vcpu;
/* Guest-specified relocation of vcpu_info. */
unsigned long vcpu_info_mfn;
struct arch_vcpu arch;
};
/* Per-domain lock can be recursively acquired in fault handlers. */
#define domain_lock(d) spin_lock_recursive(&(d)->domain_lock)
#define domain_unlock(d) spin_unlock_recursive(&(d)->domain_lock)
#define domain_is_locked(d) spin_is_locked(&(d)->domain_lock)
/* Memory event */
struct mem_event_domain
{
/* ring lock */
spinlock_t ring_lock;
/* The ring has 64 entries */
unsigned char foreign_producers;
unsigned char target_producers;
/* shared ring page */
void *ring_page;
struct page_info *ring_pg_struct;
/* front-end ring */
mem_event_front_ring_t front_ring;
/* event channel port (vcpu0 only) */
int xen_port;
/* mem_event bit for vcpu->pause_flags */
int pause_flag;
/* list of vcpus waiting for room in the ring */
struct waitqueue_head wq;
/* the number of vCPUs blocked */
unsigned int blocked;
/* The last vcpu woken up */
unsigned int last_vcpu_wake_up;
};
struct mem_event_per_domain
{
/* Memory sharing support */
struct mem_event_domain share;
/* Memory paging support */
struct mem_event_domain paging;
/* Memory access support */
struct mem_event_domain access;
};
struct domain
{
domid_t domain_id;
shared_info_t *shared_info; /* shared data area */
spinlock_t domain_lock;
spinlock_t page_alloc_lock; /* protects all the following fields */
struct page_list_head page_list; /* linked list */
struct page_list_head xenpage_list; /* linked list (size xenheap_pages) */
unsigned int tot_pages; /* number of pages currently possesed */
unsigned int outstanding_pages; /* pages claimed but not possessed */
unsigned int max_pages; /* maximum value for tot_pages */
atomic_t shr_pages; /* number of shared pages */
atomic_t paged_pages; /* number of paged-out pages */
unsigned int xenheap_pages; /* # pages allocated from Xen heap */
unsigned int max_vcpus;
/* Scheduling. */
void *sched_priv; /* scheduler-specific data */
struct cpupool *cpupool;
struct domain *next_in_list;
struct domain *next_in_hashbucket;
struct list_head rangesets;
spinlock_t rangesets_lock;
/* Event channel information. */
struct evtchn *evtchn[NR_EVTCHN_BUCKETS];
spinlock_t event_lock;
struct grant_table *grant_table;
/*
* Interrupt to event-channel mappings and other per-guest-pirq data.
* Protected by the domain's event-channel spinlock.
*/
unsigned int nr_pirqs;
struct radix_tree_root pirq_tree;
/* I/O capabilities (access to IRQs and memory-mapped I/O). */
struct rangeset *iomem_caps;
struct rangeset *irq_caps;
/* Is this an HVM guest? */
bool_t is_hvm;
#ifdef HAS_PASSTHROUGH
/* Does this guest need iommu mappings? */
bool_t need_iommu;
#endif
/* is node-affinity automatically computed? */
bool_t auto_node_affinity;
/* Is this guest fully privileged (aka dom0)? */
bool_t is_privileged;
/* Which guest this guest has privileges on */
struct domain *target;
/* Is this guest being debugged by dom0? */
bool_t debugger_attached;
/* Is this guest dying (i.e., a zombie)? */
enum { DOMDYING_alive, DOMDYING_dying, DOMDYING_dead } is_dying;
/* Domain is paused by controller software? */
bool_t is_paused_by_controller;
/* Domain's VCPUs are pinned 1:1 to physical CPUs? */
bool_t is_pinned;
/* Are any VCPUs polling event channels (SCHEDOP_poll)? */
#if MAX_VIRT_CPUS <= BITS_PER_LONG
DECLARE_BITMAP(poll_mask, MAX_VIRT_CPUS);
#else
unsigned long *poll_mask;
#endif
/* Guest has shut down (inc. reason code)? */
spinlock_t shutdown_lock;
bool_t is_shutting_down; /* in process of shutting down? */
bool_t is_shut_down; /* fully shut down? */
int shutdown_code;
/* If this is not 0, send suspend notification here instead of
* raising DOM_EXC */
int suspend_evtchn;
atomic_t pause_count;
unsigned long vm_assist;
atomic_t refcnt;
struct vcpu **vcpu;
/* Bitmask of CPUs which are holding onto this domain's state. */
cpumask_var_t domain_dirty_cpumask;
struct arch_domain arch;
void *ssid; /* sHype security subject identifier */
/* Control-plane tools handle for this domain. */
xen_domain_handle_t handle;
/* hvm_print_line() and guest_console_write() logging. */
#define DOMAIN_PBUF_SIZE 80
char *pbuf;
unsigned pbuf_idx;
spinlock_t pbuf_lock;
/* OProfile support. */
struct xenoprof *xenoprof;
int32_t time_offset_seconds;
/* Domain watchdog. */
#define NR_DOMAIN_WATCHDOG_TIMERS 2
spinlock_t watchdog_lock;
uint32_t watchdog_inuse_map;
struct timer watchdog_timer[NR_DOMAIN_WATCHDOG_TIMERS];
struct rcu_head rcu;
/*
* Hypercall deadlock avoidance lock. Used if a hypercall might
* cause a deadlock. Acquirers don't spin waiting; they preempt.
*/
spinlock_t hypercall_deadlock_mutex;
/* transcendent memory, auto-allocated on first tmem op by each domain */
void *tmem;
struct lock_profile_qhead profile_head;
/* Non-migratable and non-restoreable? */
bool_t disable_migrate;
/* Various mem_events */
struct mem_event_per_domain *mem_event;
/*
* Can be specified by the user. If that is not the case, it is
* computed from the union of all the vcpu cpu-affinity masks.
*/
nodemask_t node_affinity;
unsigned int last_alloc_node;
spinlock_t node_affinity_lock;
};
struct domain_setup_info
{
/* Initialised by caller. */
unsigned long image_addr;
unsigned long image_len;
/* Initialised by loader: Public. */
unsigned long v_start;
unsigned long v_end;
unsigned long v_kernstart;
unsigned long v_kernend;
unsigned long v_kernentry;
#define PAEKERN_no 0
#define PAEKERN_yes 1
#define PAEKERN_extended_cr3 2
#define PAEKERN_bimodal 3
unsigned int pae_kernel;
/* Initialised by loader: Private. */
unsigned long elf_paddr_offset;
unsigned int load_symtab;
unsigned long symtab_addr;
unsigned long symtab_len;
};
/* Protect updates/reads (resp.) of domain_list and domain_hash. */
extern spinlock_t domlist_update_lock;
extern rcu_read_lock_t domlist_read_lock;
extern struct vcpu *idle_vcpu[NR_CPUS];
#define is_idle_domain(d) ((d)->domain_id == DOMID_IDLE)
#define is_idle_vcpu(v) (is_idle_domain((v)->domain))
#define DOMAIN_DESTROYED (1<<31) /* assumes atomic_t is >= 32 bits */
#define put_domain(_d) \
if ( atomic_dec_and_test(&(_d)->refcnt) ) domain_destroy(_d)
/*
* Use this when you don't have an existing reference to @d. It returns
* FALSE if @d is being destroyed.
*/
static always_inline int get_domain(struct domain *d)
{
atomic_t old, new, seen = d->refcnt;
do
{
old = seen;
if ( unlikely(_atomic_read(old) & DOMAIN_DESTROYED) )
return 0;
_atomic_set(new, _atomic_read(old) + 1);
seen = atomic_compareandswap(old, new, &d->refcnt);
}
while ( unlikely(_atomic_read(seen) != _atomic_read(old)) );
return 1;
}
/*
* Use this when you already have, or are borrowing, a reference to @d.
* In this case we know that @d cannot be destroyed under our feet.
*/
static inline void get_knownalive_domain(struct domain *d)
{
atomic_inc(&d->refcnt);
ASSERT(!(atomic_read(&d->refcnt) & DOMAIN_DESTROYED));
}
int domain_set_node_affinity(struct domain *d, const nodemask_t *affinity);
void domain_update_node_affinity(struct domain *d);
struct domain *domain_create(
domid_t domid, unsigned int domcr_flags, uint32_t ssidref);
/* DOMCRF_hvm: Create an HVM domain, as opposed to a PV domain. */
#define _DOMCRF_hvm 0
#define DOMCRF_hvm (1U<<_DOMCRF_hvm)
/* DOMCRF_hap: Create a domain with hardware-assisted paging. */
#define _DOMCRF_hap 1
#define DOMCRF_hap (1U<<_DOMCRF_hap)
/* DOMCRF_s3_integrity: Create a domain with tboot memory integrity protection
by tboot */
#define _DOMCRF_s3_integrity 2
#define DOMCRF_s3_integrity (1U<<_DOMCRF_s3_integrity)
/* DOMCRF_dummy: Create a dummy domain (not scheduled; not on domain list) */
#define _DOMCRF_dummy 3
#define DOMCRF_dummy (1U<<_DOMCRF_dummy)
/* DOMCRF_oos_off: dont use out-of-sync optimization for shadow page tables */
#define _DOMCRF_oos_off 4
#define DOMCRF_oos_off (1U<<_DOMCRF_oos_off)
/*
* rcu_lock_domain_by_id() is more efficient than get_domain_by_id().
* This is the preferred function if the returned domain reference
* is short lived, but it cannot be used if the domain reference needs
* to be kept beyond the current scope (e.g., across a softirq).
* The returned domain reference must be discarded using rcu_unlock_domain().
*/
struct domain *rcu_lock_domain_by_id(domid_t dom);
/*
* As above function, but resolves DOMID_SELF to current domain
*/
struct domain *rcu_lock_domain_by_any_id(domid_t dom);
/*
* As rcu_lock_domain_by_id(), but will fail EPERM or ESRCH rather than resolve
* to local domain.
*/
int rcu_lock_remote_domain_by_id(domid_t dom, struct domain **d);
/*
* As rcu_lock_remote_domain_by_id() but will fail EINVAL if the domain is
* dying.
*/
int rcu_lock_live_remote_domain_by_id(domid_t dom, struct domain **d);
/* Finish a RCU critical region started by rcu_lock_domain_by_id(). */
static inline void rcu_unlock_domain(struct domain *d)
{
if ( d != current->domain )
rcu_read_unlock(&domlist_read_lock);
}
static inline struct domain *rcu_lock_domain(struct domain *d)
{
if ( d != current->domain )
|
