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
|
/*
* Copyright (C) 2012 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <clocksource/arm_arch_timer.h>
#include <asm/arch_timer.h>
#include <asm/kvm_hyp.h>
#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
#include "trace.h"
static struct timecounter *timecounter;
static unsigned int host_vtimer_irq;
static u32 host_vtimer_irq_flags;
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
vcpu_vtimer(vcpu)->active_cleared_last = false;
}
static u64 kvm_phys_timer_read(void)
{
return timecounter->cc->read(timecounter->cc);
}
static bool timer_is_armed(struct arch_timer_cpu *timer)
{
return timer->armed;
}
/* timer_arm: as in "arm the timer", not as in ARM the company */
static void timer_arm(struct arch_timer_cpu *timer, u64 ns)
{
timer->armed = true;
hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns),
HRTIMER_MODE_ABS);
}
static void timer_disarm(struct arch_timer_cpu *timer)
{
if (timer_is_armed(timer)) {
hrtimer_cancel(&timer->timer);
cancel_work_sync(&timer->expired);
timer->armed = false;
}
}
static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
{
struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
/*
* We disable the timer in the world switch and let it be
* handled by kvm_timer_sync_hwstate(). Getting a timer
* interrupt at this point is a sure sign of some major
* breakage.
*/
pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu);
return IRQ_HANDLED;
}
/*
* Work function for handling the backup timer that we schedule when a vcpu is
* no longer running, but had a timer programmed to fire in the future.
*/
static void kvm_timer_inject_irq_work(struct work_struct *work)
{
struct kvm_vcpu *vcpu;
vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
/*
* If the vcpu is blocked we want to wake it up so that it will see
* the timer has expired when entering the guest.
*/
kvm_vcpu_kick(vcpu);
}
static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
{
u64 cval, now;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
cval = vtimer->cnt_cval;
now = kvm_phys_timer_read() - vtimer->cntvoff;
if (now < cval) {
u64 ns;
ns = cyclecounter_cyc2ns(timecounter->cc,
cval - now,
timecounter->mask,
&timecounter->frac);
return ns;
}
return 0;
}
static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
{
struct arch_timer_cpu *timer;
struct kvm_vcpu *vcpu;
u64 ns;
timer = container_of(hrt, struct arch_timer_cpu, timer);
vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
/*
* Check that the timer has really expired from the guest's
* PoV (NTP on the host may have forced it to expire
* early). If we should have slept longer, restart it.
*/
ns = kvm_timer_compute_delta(vcpu);
if (unlikely(ns)) {
hrtimer_forward_now(hrt, ns_to_ktime(ns));
return HRTIMER_RESTART;
}
schedule_work(&timer->expired);
return HRTIMER_NORESTART;
}
static bool kvm_timer_irq_can_fire(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
return !(vtimer->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
(vtimer->cnt_ctl & ARCH_TIMER_CTRL_ENABLE);
}
bool kvm_timer_should_fire(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
u64 cval, now;
if (!kvm_timer_irq_can_fire(vcpu))
return false;
cval = vtimer->cnt_cval;
now = kvm_phys_timer_read() - vtimer->cntvoff;
return cval <= now;
}
static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
{
int ret;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
BUG_ON(!vgic_initialized(vcpu->kvm));
vtimer->active_cleared_last = false;
vtimer->irq.level = new_level;
trace_kvm_timer_update_irq(vcpu->vcpu_id, vtimer->irq.irq,
vtimer->irq.level);
ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
vtimer->irq.irq,
vtimer->irq.level);
WARN_ON(ret);
}
/*
* Check if there was a change in the timer state (should we raise or lower
* the line level to the GIC).
*/
static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
/*
* If userspace modified the timer registers via SET_ONE_REG before
* the vgic was initialized, we mustn't set the vtimer->irq.level value
* because the guest would never see the interrupt. Instead wait
* until we call this function from kvm_timer_flush_hwstate.
*/
if (!vgic_initialized(vcpu->kvm) || !timer->enabled)
return -ENODEV;
if (kvm_timer_should_fire(vcpu) != vtimer->irq.level)
kvm_timer_update_irq(vcpu, !vtimer->irq.level);
return 0;
}
/*
* Schedule the background timer before calling kvm_vcpu_block, so that this
* thread is removed from its waitqueue and made runnable when there's a timer
* interrupt to handle.
*/
void kvm_timer_schedule(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
BUG_ON(timer_is_armed(timer));
/*
* No need to schedule a background timer if the guest timer has
* already expired, because kvm_vcpu_block will return before putting
* the thread to sleep.
*/
if (kvm_timer_should_fire(vcpu))
return;
/*
* If the timer is not capable of raising interrupts (disabled or
* masked), then there's no more work for us to do.
*/
if (!kvm_timer_irq_can_fire(vcpu))
return;
/* The timer has not yet expired, schedule a background timer */
timer_arm(timer, kvm_timer_compute_delta(vcpu));
}
void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
timer_disarm(timer);
}
/**
* kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
* @vcpu: The vcpu pointer
*
* Check if the virtual timer has expired while we were running in the host,
* and inject an interrupt if that was the case.
*/
void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
bool phys_active;
int ret;
if (kvm_timer_update_state(vcpu))
return;
/*
* If we enter the guest with the virtual input level to the VGIC
* asserted, then we have already told the VGIC what we need to, and
* we don't need to exit from the guest until the guest deactivates
* the already injected interrupt, so therefore we should set the
* hardware active state to prevent unnecessary exits from the guest.
*
* Also, if we enter the guest with the virtual timer interrupt active,
* then it must be active on the physical distributor, because we set
* the HW bit and the guest must be able to deactivate the virtual and
* physical interrupt at the same time.
*
* Conversely, if the virtual input level is deasserted and the virtual
* interrupt is not active, then always clear the hardware active state
* to ensure that hardware interrupts from the timer triggers a guest
* exit.
*/
phys_active = vtimer->irq.level ||
kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
/*
* We want to avoid hitting the (re)distributor as much as
* possible, as this is a potentially expensive MMIO access
* (not to mention locks in the irq layer), and a solution for
* this is to cache the "active" state in memory.
*
* Things to consider: we cannot cache an "active set" state,
* because the HW can change this behind our back (it becomes
* "clear" in the HW). We must then restrict the caching to
* the "clear" state.
*
* The cache is invalidated on:
* - vcpu put, indicating that the HW cannot be trusted to be
* in a sane state on the next vcpu load,
* - any change in the interrupt state
*
* Usage conditions:
* - cached value is "active clear"
* - value to be programmed is "active clear"
*/
if (vtimer->active_cleared_last && !phys_active)
return;
ret = irq_set_irqchip_state(host_vtimer_irq,
|