summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/kvm.c
blob: 8dc44662394bebadcbbcbb70e6e938adbb2e8ced (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
/*
 * 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/module.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 <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/tlbflush.h>

#define MMU_QUEUE_SIZE 1024

static int kvmapf = 1;

static int parse_no_kvmapf(char *arg)
{
        kvmapf = 0;
        return 0;
}

early_param("no-kvmapf", parse_no_kvmapf);

struct kvm_para_state {
	u8 mmu_queue[MMU_QUEUE_SIZE];
	int mmu_queue_len;
};

static DEFINE_PER_CPU(struct kvm_para_state, para_state);
static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);

static struct kvm_para_state *kvm_para_state(void)
{
	return &per_cpu(para_state, raw_smp_processor_id());
}

/*
 * 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;
	wait_queue_head_t wq;
	u32 token;
	int cpu;
	bool halted;
	struct mm_struct *mm;
};

static struct kvm_task_sleep_head {
	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;
	DEFINE_WAIT(wait);
	int cpu, idle;

	cpu = get_cpu();
	idle = idle_cpu(cpu);
	put_cpu();

	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);
		spin_unlock(&b->lock);
		return;
	}

	n.token = token;
	n.cpu = smp_processor_id();
	n.mm = current->active_mm;
	n.halted = idle || preempt_count() > 1;
	atomic_inc(&n.mm->mm_count);
	init_waitqueue_head(&n.wq);
	hlist_add_head(&n.link, &b->list);
	spin_unlock(&b->lock);

	for (;;) {
		if (!n.halted)
			prepare_to_wait(&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.
			 */
			native_safe_halt();
			local_irq_disable();
		}
	}
	if (!n.halted)
		finish_wait(&n.wq, &wait);

	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->mm)
		return;
	mmdrop(n->mm);
	if (n->halted)
		smp_send_reschedule(n->cpu);
	else if (waitqueue_active(&n->wq))
		wake_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];
		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);
		}
		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:
	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 = kmalloc(sizeof(*n), GFP_ATOMIC);
		if (!n) {
			/*
			 * Allocation failed! Busy wait while other cpu
			 * handles async PF.
			 */
			spin_unlock(&b->lock);
			cpu_relax();
			goto again;
		}
		n->token = token;
		n->cpu = smp_processor_id();
		n->mm = NULL;
		init_waitqueue_head(&n->wq);
		hlist_add_head(&n->link, &b->list);
	} else
		apf_task_wake_one(n);
	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 (__get_cpu_var(apf_reason).enabled) {
		reason = __get_cpu_var(apf_reason).reason;
		__get_cpu_var(apf_reason).reason = 0;
	}

	return reason;
}
EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);

dotraplinkage void __kprobes
do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
{
	switch (kvm_read_and_reset_pf_reason()) {
	default:
		do_page_fault(regs, error_code);
		break;
	case KVM_PV_REASON_PAGE_NOT_PRESENT:
		/* page is swapped out by the host. */
		kvm_async_pf_task_wait((u32)read_cr2());
		break;
	case KVM_PV_REASON_PAGE_READY:
		kvm_async_pf_task_wake((u32)read_cr2());
		break;
	}
}

static void kvm_mmu_op(void *buffer, unsigned len)
{
	int r;
	unsigned long a1, a2;

	do {
		a1 = __pa(buffer);
		a2 = 0;   /* on i386 __pa() always returns <4G */
		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
		buffer += r;
		len -= r;
	} while (len);
}

static void mmu_queue_flush(struct kvm_para_state *state)
{
	if (state->mmu_queue_len) {
		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
		state->mmu_queue_len = 0;
	}
}

static void kvm_deferred_mmu_op(void *buffer, int len)
{
	struct kvm_para_state *state = kvm_para_state();

	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
		kvm_mmu_op(buffer, len);
		return;
	}
	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
		mmu_queue_flush(state);
	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
	state->mmu_queue_len += len;
}

static void kvm_mmu_write(void *dest, u64 val)
{
	__u64 pte_phys;
	struct kvm_mmu_op_write_pte wpte;

#ifdef CONFIG_HIGHPTE
	struct page *page;
	unsigned long dst = (unsigned long) dest;

	page = kmap_atomic_to_page(dest);
	pte_phys = page_to_pfn(page);
	pte_phys <<= PAGE_SHIFT;
	pte_phys += (dst & ~(PAGE_MASK));
#else
	pte_phys = (unsigned long)__pa(dest);
#endif
	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
	wpte.pte_val = val;
	wpte.pte_phys = pte_phys;

	kvm_deferred_mmu_op(&wpte, sizeof wpte);
}

/*
 * We only need to hook operations that are MMU writes.  We hook these so that
 * we can use lazy MMU mode to batch these operations.  We could probably
 * improve the performance of the host code if we used some of the information
 * here to simplify processing of batched writes.
 */
static void kvm_set_pte(pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
			   pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
	kvm_mmu_write(pmdp, pmd_val(pmd));
}

#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_pte_clear(struct mm_struct *mm,
			  unsigned long addr, pte_t *ptep)
{
	kvm_mmu_write(ptep, 0);
}

static void kvm_pmd_clear(pmd_t *pmdp)
{
	kvm_mmu_write(pmdp, 0);
}
#endif

static void kvm_set_pud(pud_t *pudp, pud_t pud)
{
	kvm_mmu_write(pudp, pud_val(pud));
}

#if PAGETABLE_LEVELS == 4
static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
	kvm_mmu_write(pgdp, pgd_val(pgd));
}
#endif
#endif /* PAGETABLE_LEVELS >= 3 */

static void kvm_flush_tlb(void)
{
	struct kvm_mmu_op_flush_tlb ftlb = {
		.header.op = KVM_MMU_OP_FLUSH_TLB,
	};

	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
}

static void kvm_release_pt(unsigned long pfn)
{
	struct kvm_mmu_op_release_pt rpt = {
		.header.op = KVM_MMU_OP_RELEASE_PT,
		.pt_phys = (u64)pfn << PAGE_SHIFT,
	};

	kvm_mmu_op(&rpt, sizeof rpt);
}

static void kvm_enter_lazy_mmu(void)
{
	paravirt_enter_lazy_mmu();
}

static void kvm_leave_lazy_mmu(void)
{
	struct kvm_para_state *state = kvm_para_state();

	mmu_queue_flush(state);
	paravirt_leave_lazy_mmu();
}

static void __init paravirt_ops_setup(void)
{
	pv_info.name = "KVM";
	pv_info.paravirt_enabled = 1;

	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
		pv_cpu_ops.io_delay = kvm_io_delay;

	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
		pv_mmu_ops.set_pte = kvm_set_pte;
		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
		pv_mmu_ops.set_pmd = kvm_set_pmd;
#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
		pv_mmu_ops.pte_clear = kvm_pte_clear;
		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
#endif
		pv_mmu_ops.set_pud = kvm_set_pud;
#if PAGETABLE_LEVELS == 4
		pv_mmu_ops.set_pgd = kvm_set_pgd;
#endif
#endif
		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
		pv_mmu_ops.release_pte = kvm_release_pt;
		pv_mmu_ops.release_pmd = kvm_release_pt;
		pv_mmu_ops.release_pud = kvm_release_pt;

		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
	}
#ifdef CONFIG_X86_IO_APIC
	no_timer_check = 1;
#endif
}

void __cpuinit kvm_guest_cpu_init(void)
{
	if (!kvm_para_available())
		return;

	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
		u64 pa = __pa(&__get_cpu_var(apf_reason));

#ifdef CONFIG_PREEMPT
		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
		__get_cpu_var(apf_reason).enabled = 1;
		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
		       smp_processor_id());
	}
}

static void kvm_pv_disable_apf(void *unused)
{
	if (!__get_cpu_var(apf_reason).enabled)
		return;

	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
	__get_cpu_var(apf_reason).enabled = 0;

	printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
	       smp_processor_id());
}

static int kvm_pv_reboot_notify(struct notifier_block *nb,
				unsigned long code, void *unused)
{
	if (code == SYS_RESTART)
		on_each_cpu(kvm_pv_disable_apf, NULL, 1);
	return NOTIFY_DONE;
}

static struct notifier_block kvm_pv_reboot_nb = {
	.notifier_call = kvm_pv_reboot_notify,
};

#ifdef CONFIG_SMP
static void __init kvm_smp_prepare_boot_cpu(void)
{
#ifdef CONFIG_KVM_CLOCK
	WARN_ON(kvm_register_clock("primary cpu clock"));
#endif
	kvm_guest_cpu_init();
	native_smp_prepare_boot_cpu();
}

static void kvm_guest_cpu_online(void *dummy)
{
	kvm_guest_cpu_init();
}

static void kvm_guest_cpu_offline(void *dummy)
{
	kvm_pv_disable_apf(NULL);
	apf_task_wake_all();
}

static int __cpuinit kvm_cpu_notify(struct notifier_block *self,
				    unsigned long action, void *hcpu)
{
	int cpu = (unsigned long)hcpu;
	switch (action) {
	case CPU_ONLINE:
	case CPU_DOWN_FAILED:
	case CPU_ONLINE_FROZEN:
		smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0);
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata kvm_cpu_notifier = {
        .notifier_call  = kvm_cpu_notify,
};
#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++)
		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;

#ifdef CONFIG_SMP
	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
	register_cpu_notifier(&kvm_cpu_notifier);
#else
	kvm_guest_cpu_init();
#endif
}