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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* X86 specific Hyper-V initialization code.
*
* Copyright (C) 2016, Microsoft, Inc.
*
* Author : K. Y. Srinivasan <kys@microsoft.com>
*/
#include <linux/acpi.h>
#include <linux/efi.h>
#include <linux/types.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>
#include <asm/idtentry.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/cpuhotplug.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
/* Storage to save the hypercall page temporarily for hibernation */
static void *hv_hypercall_pg_saved;
u32 *hv_vp_index;
EXPORT_SYMBOL_GPL(hv_vp_index);
struct hv_vp_assist_page **hv_vp_assist_page;
EXPORT_SYMBOL_GPL(hv_vp_assist_page);
void __percpu **hyperv_pcpu_input_arg;
EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
u32 hv_max_vp_index;
EXPORT_SYMBOL_GPL(hv_max_vp_index);
void *hv_alloc_hyperv_page(void)
{
BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
return (void *)__get_free_page(GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
void *hv_alloc_hyperv_zeroed_page(void)
{
BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
}
EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);
void hv_free_hyperv_page(unsigned long addr)
{
free_page(addr);
}
EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
static int hv_cpu_init(unsigned int cpu)
{
u64 msr_vp_index;
struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
void **input_arg;
struct page *pg;
input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
if (unlikely(!pg))
return -ENOMEM;
*input_arg = page_address(pg);
hv_get_vp_index(msr_vp_index);
hv_vp_index[smp_processor_id()] = msr_vp_index;
if (msr_vp_index > hv_max_vp_index)
hv_max_vp_index = msr_vp_index;
if (!hv_vp_assist_page)
return 0;
/*
* The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section
* 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure
* we always write the EOI MSR in hv_apic_eoi_write() *after* the
* EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may
* not be stopped in the case of CPU offlining and the VM will hang.
*/
if (!*hvp) {
*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
}
if (*hvp) {
u64 val;
val = vmalloc_to_pfn(*hvp);
val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
}
return 0;
}
static void (*hv_reenlightenment_cb)(void);
static void hv_reenlightenment_notify(struct work_struct *dummy)
{
struct hv_tsc_emulation_status emu_status;
rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
/* Don't issue the callback if TSC accesses are not emulated */
if (hv_reenlightenment_cb && emu_status.inprogress)
hv_reenlightenment_cb();
}
static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);
void hyperv_stop_tsc_emulation(void)
{
u64 freq;
struct hv_tsc_emulation_status emu_status;
rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
emu_status.inprogress = 0;
wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
tsc_khz = div64_u64(freq, 1000);
}
EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
static inline bool hv_reenlightenment_available(void)
{
/*
* Check for required features and priviliges to make TSC frequency
* change notifications work.
*/
return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT;
}
DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_reenlightenment)
{
ack_APIC_irq();
inc_irq_stat(irq_hv_reenlightenment_count);
schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
}
void set_hv_tscchange_cb(void (*cb)(void))
{
struct hv_reenlightenment_control re_ctrl = {
.vector = HYPERV_REENLIGHTENMENT_VECTOR,
.enabled = 1,
.target_vp = hv_vp_index[smp_processor_id()]
};
struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
if (!hv_reenlightenment_available()) {
pr_warn("Hyper-V: reenlightenment support is unavailable\n");
return;
}
hv_reenlightenment_cb = cb;
/* Make sure callback is registered before we write to MSRs */
wmb();
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
}
EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);
void clear_hv_tscchange_cb(void)
{
struct hv_reenlightenment_control re_ctrl;
if (!hv_reenlightenment_available())
return;
rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
re_ctrl.enabled = 0;
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
hv_reenlightenment_cb = NULL;
}
EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);
static int hv_cpu_die(unsigned int cpu)
{
struct hv_reenlightenment_control re_ctrl;
unsigned int new_cpu;
unsigned long flags;
void **input_arg;
void *input_pg = NULL;
local_irq_save(flags);
input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
input_pg = *input_arg;
*input_arg = NULL;
local_irq_restore(flags);
free_page((unsigned long)input_pg);
if (hv_vp_assist_page && hv_vp_assist_page[cpu])
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
if (hv_reenlightenment_cb == NULL)
return 0;
rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
if (re_ctrl.target_vp == hv_vp_index[cpu]) {
/*
* Reassign reenlightenment notifications to some other online
* CPU or just disable the feature if there are no online CPUs
* left (happens on hibernation).
*/
new_cpu = cpumask_any_but(cpu_online_mask, cpu);
if (new_cpu < nr_cpu_ids)
re_ctrl.target_vp = hv_vp_index[new_cpu];
else
re_ctrl.enabled = 0;
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
}
return 0;
}
static int __init hv_pci_init(void)
{
int gen2vm = efi_enabled(EFI_BOOT);
/*
* For Generation-2 VM, we exit from pci_arch_init() by returning 0.
* The purpose is to suppress the harmless warning:
* "PCI: Fatal: No config space access function found"
*/
if (gen2vm)
return 0;
/* For Generation-1 VM, we'll proceed in pci_arch_init(). */
return 1;
}
static int hv_suspend(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
int ret;
/*
* Reset the hypercall page as it is going to be invalidated
* accross hibernation. Setting hv_hypercall_pg to NULL ensures
* that any subsequent hypercall operation fails safely instead of
* crashing due to an access of an invalid page. The hypercall page
* pointer is restored on resume.
*/
hv_hypercall_pg_saved = hv_hypercall_pg;
hv_hypercall_pg = NULL;
/* Disable the hypercall page in the hypervisor */
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 0;
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
ret = hv_cpu_die(0);
return ret;
}
static void hv_resume(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
int ret;
ret = hv_cpu_init(0);
WARN_ON(ret);
/* Re-enable the hypercall page */
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
hypercall_msr.guest_physical_address =
vmalloc_to_pfn(hv_hypercall_pg_saved);
wrmsrl(HV_X64_MSR_HYPERCALL,
|