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
|
/*
* KVM paravirt_ops implementation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
* Copyright IBM Corporation, 2007
* Authors: Anthony Liguori <aliguori@us.ibm.com>
*/
#include <linux/context_tracking.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kvm_para.h>
#include <linux/cpu.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hardirq.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kprobes.h>
#include <linux/debugfs.h>
#include <linux/nmi.h>
#include <linux/swait.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/tlbflush.h>
#include <asm/idle.h>
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
#include <asm/kvm_guest.h>
static int kvmapf = 1;
static int parse_no_kvmapf(char *arg)
{
kvmapf = 0;
return 0;
}
early_param("no-kvmapf", parse_no_kvmapf);
static int steal_acc = 1;
static int parse_no_stealacc(char *arg)
{
steal_acc = 0;
return 0;
}
early_param("no-steal-acc", parse_no_stealacc);
static int kvmclock_vsyscall = 1;
static int parse_no_kvmclock_vsyscall(char *arg)
{
kvmclock_vsyscall = 0;
return 0;
}
early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
static int has_steal_clock = 0;
/*
* No need for any "IO delay" on KVM
*/
static void kvm_io_delay(void)
{
}
#define KVM_TASK_SLEEP_HASHBITS 8
#define KVM_TASK_SLEEP_HASHSIZE (1<<KVM_TASK_SLEEP_HASHBITS)
struct kvm_task_sleep_node {
struct hlist_node link;
struct swait_queue_head wq;
u32 token;
int cpu;
bool halted;
};
static struct kvm_task_sleep_head {
raw_spinlock_t lock;
struct hlist_head list;
} async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
u32 token)
{
struct hlist_node *p;
hlist_for_each(p, &b->list) {
struct kvm_task_sleep_node *n =
hlist_entry(p, typeof(*n), link);
if (n->token == token)
return n;
}
return NULL;
}
void kvm_async_pf_task_wait(u32 token)
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
struct kvm_task_sleep_node n, *e;
DECLARE_SWAITQUEUE(wait);
rcu_irq_enter();
raw_spin_lock(&b->lock);
e = _find_apf_task(b, token);
if (e) {
/* dummy entry exist -> wake up was delivered ahead of PF */
hlist_del(&e->link);
kfree(e);
raw_spin_unlock(&b->lock);
rcu_irq_exit();
return;
}
n.token = token;
n.cpu = smp_processor_id();
n.halted = is_idle_task(current) || preempt_count() > 1;
init_swait_queue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
raw_spin_unlock(&b->lock);
for (;;) {
if (!n.halted)
prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
if (hlist_unhashed(&n.link))
break;
if (!n.halted) {
local_irq_enable();
schedule();
local_irq_disable();
} else {
/*
* We cannot reschedule. So halt.
*/
rcu_irq_exit();
native_safe_halt();
rcu_irq_enter();
local_irq_disable();
}
}
if (!n.halted)
finish_swait(&n.wq, &wait);
rcu_irq_exit();
return;
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
hlist_del_init(&n->link);
if (n->halted)
smp_send_reschedule(n->cpu);
else if (swait_active(&n->wq))
swake_up(&n->wq);
}
static void apf_task_wake_all(void)
{
int i;
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
struct hlist_node *p, *next;
struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
raw_spin_lock(&b->lock);
hlist_for_each_safe(p, next, &b->list) {
struct kvm_task_sleep_node *n =
hlist_entry(p, typeof(*n), link);
if (n->cpu == smp_processor_id())
apf_task_wake_one(n);
}
raw_spin_unlock(&b->lock);
}
}
void kvm_async_pf_task_wake(u32 token)
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
struct kvm_task_sleep_node *n;
if (token == ~0) {
apf_task_wake_all();
return;
}
again:
raw_spin_lock(&b->lock);
n = _find_apf_task(b, token);
if (!n) {
/*
* async PF was not yet handled.
* Add dummy entry for the token.
*/
n = kzalloc(sizeof(*n), GFP_ATOMIC);
if (!n) {
/*
* Allocation failed! Busy wait while other cpu
* handles async PF.
*/
raw_spin_unlock(&b->lock);
cpu_relax();
goto again;
}
n->token = token;
n->cpu = smp_processor_id();
init_swait_queue_head(&n->wq);
hlist_add_head(&n->link, &b->list);
} else
apf_task_wake_one(n);
raw_spin_unlock(&b->lock);
return;
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
u32 kvm_read_and_reset_pf_reason(void)
{
u32 reason = 0;
if (__this_cpu_read(apf_reason.enabled)) {
reason = __this_cpu_read(apf_reason.reason);
__this_cpu_write(apf_reason.reason, 0);
}
return reason;
}
EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
dotraplinkage void
do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
{
enum ctx_state prev_state;
switch (kvm_read_and_reset_pf_reason()) {
default:
trace_do_page_fault(regs, error_code);
break;
case KVM_PV_REASON_PAGE_NOT_PRESENT:
/* page is swapped out by the host. */
prev_state = exception_enter();
exit_idle();
kvm_async_pf_task_wait((u32)read_cr2());
exception_exit(prev_state);
break;
case KVM_PV_REASON_PAGE_READY:
rcu_irq_enter();
exit_idle();
kvm_async_pf_task_wake((u32)read_cr2());
rcu_irq_exit();
break;
}
}
NOKPROBE_SYMBOL(do_async_page_fault);
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
pv_cpu_ops.io_delay = kvm_io_delay;
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
#endif
}
static void kvm_register_steal_time(void)
{
int cpu = smp_processor_id();
struct kvm_steal_time *st = &per_cpu(steal_time, cpu);
if (!has_steal_clock)
return;
wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
pr_info("kvm-stealtime: cpu %d, msr %llx\n",
cpu, (unsigned long long) slow_virt_to_phys(st));
}
static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;
static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
{
/**
* This relies on __test_and_clear_bit to modify the memory
* in a way that is atomic with respect to the local CPU.
* The hypervisor only accesses this memory from the local CPU so
* there's no need for lock or memory barriers.
* An optimization barrier is implied in apic write.
*/
if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
return;
apic_write(APIC_EOI, APIC_EOI_ACK);
}
static void kvm_guest_cpu_init(void)
{
if (!kvm_para_available())
return;
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
#ifdef CONFIG_PREEMPT
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
__this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
unsigned long pa;
/* Size alignment is implied but just to make it explicit. */
BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
__this_cpu_write(kvm_apic_eoi, 0);
pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
| KVM_MSR_ENABLED;
wrmsrl(MSR_KVM_PV_EOI_EN, pa);
}
if (has_steal_clock)
kvm_register_steal_time();
}
static void kvm_pv_disable_apf(void)
{
if (!__this_cpu_read(apf_reason.enabled))
return;
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
__this_cpu_write(apf_reason.enabled, 0);
printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
smp_processor_id());
}
static void kvm_pv_guest_cpu_reboot(void *unused)
{
/*
* We disable PV EOI before we load a new kernel by kexec,
* since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory.
* New kernel can re-enable when it boots.
*/
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
wrmsrl(MSR_KVM_PV_EOI_EN, 0);
kvm_pv_disable_apf();
kvm_disable_steal_time();
}
static int kvm_pv_reboot_notify(struct notifier_block *nb,
unsigned long code, void *unused)
{
if (code == SYS_RESTART)
on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1);
return NOTIFY_DONE;
}
static struct notifier_block kvm_pv_reboot_nb = {
.notifier_call = kvm_pv_reboot_notify,
};
static u64 kvm_steal_clock(int cpu)
{
u64 steal;
struct kvm_steal_time *src;
int version;
src = &per_cpu(steal_time, cpu);
do {
version = src->version;
rmb();
steal = src->steal;
rmb();
} while ((version & 1) || (version != src->version));
return steal;
}
void kvm_disable_steal_time(void)
{
if (!has_steal_clock)
return;
wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
}
#ifdef CONFIG_SMP
static void __init kvm_smp_prepare_boot_cpu(void)
{
kvm_guest_cpu_init();
native_smp_prepare_boot_cpu();
kvm_spinlock_init();
}
static void kvm_guest_cpu_offline(void)
{
kvm_disable_steal_time();
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
wrmsrl(MSR_KVM_PV_EOI_EN, 0);
kvm_pv_disable_apf();
apf_task_wake_all();
}
static int kvm_cpu_online(unsigned int cpu)
{
local_irq_disable();
kvm_guest_cpu_init();
local_irq_enable();
return 0;
}
static int kvm_cpu_down_prepare(unsigned int cpu)
{
local_irq_disable();
kvm_guest_cpu_offline();
local_irq_enable();
return 0;
}
#endif
static void __init kvm_apf_trap_init(void)
{
set_intr_gate(14, async_page_fault);
}
void __init kvm_guest_init(void)
{
int i;
if (!kvm_para_available())
return;
paravirt_ops_setup();
register_reboot_notifier(&kvm_pv_reboot_nb);
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
raw_spin_lock_init(&async_pf_sleepers[i].lock);
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
x86_init.irqs.trap_init = kvm_apf_trap_init;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
pv_time_ops.steal_clock = kvm_steal_clock;
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
if (kvmclock_vsyscall)
kvm_setup_vsyscall_timeinfo();
#ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
kvm_cpu_online, kvm_cpu_down_prepare) < 0)
pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
#else
kvm_guest_cpu_init();
#endif
/*
* Hard lockup detection is enabled by default. Disable it, as guests
* can get false positives too easily, for example if the host is
* overcommitted.
*/
hardlockup_detector_disable();
}
static noinline uint32_t __kvm_cpuid_base(void)
{
if (boot_cpu_data.cpuid_level < 0)
return 0; /* So we don't blow up on old processors */
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
return 0;
}
static inline uint32_t kvm_cpuid_base(void)
{
static int kvm_cpuid_base = -1;
if (kvm_cpuid_base == -1)
kvm_cpuid_base = __kvm_cpuid_base();
return kvm_cpuid_base;
}
bool kvm_para_available(void)
{
return kvm_cpuid_base() != 0;
}
EXPORT_SYMBOL_GPL(kvm_para_available);
unsigned int kvm_arch_para_features(void)
{
return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
}
static uint32_t __init kvm_detect(void)
{
return kvm_cpuid_base();
}
const struct hypervisor_x86 x86_hyper_kvm __refconst = {
.name = "KVM",
.detect = kvm_detect,
.x2apic_available = kvm_para_available,
};
EXPORT_SYMBOL_GPL(x86_hyper_kvm);
static __init int activate_jump_labels(void)
{
if (has_steal_clock) {
static_key_slow_inc(¶virt_steal_enabled);
if (steal_acc)
static_key_slow_inc(¶virt_steal_rq_enabled);
}
return 0;
}
arch_initcall(activate_jump_labels);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
static void kvm_kick_cpu(int cpu)
{
int apicid;
unsigned long flags = 0;
apicid = per_cpu(x86_cpu_to_apicid, cpu);
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
#include <asm/qspinlock.h>
static void kvm_wait(u8 *ptr, u8 val)
{
unsigned long flags;
if (in_nmi())
return;
local_irq_save(flags);
if (READ_ONCE(*ptr) != val)
goto out;
/*
* halt until it's our turn and kicked. Note that we do safe halt
* for irq enabled case to avoid hang when lock info is overwritten
* in irq spinlock slowpath and no spurious interrupt occur to save us.
*/
if (arch_irqs_disabled_flags(flags))
halt();
else
safe_halt();
out:
local_irq_restore(flags);
}
__visible bool __kvm_vcpu_is_preempted(int cpu)
{
struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
return !!src->preempted;
}
PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
void __init kvm_spinlock_init(void)
{
if (!kvm_para_available())
return;
/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
__pv_init_lock_hash();
pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = kvm_wait;
pv_lock_ops.kick = kvm_kick_cpu;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
pv_lock_ops.vcpu_is_preempted =
PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
}
}
static __init int kvm_spinlock_init_jump(void)
{
if (!kvm_para_available())
return 0;
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return 0;
static_key_slow_inc(¶virt_ticketlocks_enabled);
printk(KERN_INFO "KVM setup paravirtual spinlock\n");
return 0;
}
early_initcall(kvm_spinlock_init_jump);
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
|