summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/kvmclock.c
blob: d37ed4e1d0338c8b21ad461f5d2672cead15629a (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*  KVM paravirtual clock driver. A clocksource implementation
    Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc.
*/

#include <linux/clocksource.h>
#include <linux/kvm_para.h>
#include <asm/pvclock.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/cpuhotplug.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/set_memory.h>

#include <asm/hypervisor.h>
#include <asm/mem_encrypt.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
#include <asm/kvmclock.h>

static int kvmclock __initdata = 1;
static int kvmclock_vsyscall __initdata = 1;
static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
static u64 kvm_sched_clock_offset __ro_after_init;

static int __init parse_no_kvmclock(char *arg)
{
	kvmclock = 0;
	return 0;
}
early_param("no-kvmclock", parse_no_kvmclock);

static int __init parse_no_kvmclock_vsyscall(char *arg)
{
	kvmclock_vsyscall = 0;
	return 0;
}
early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);

/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
#define HVC_BOOT_ARRAY_SIZE \
	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))

static struct pvclock_vsyscall_time_info
			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
static struct pvclock_wall_clock wall_clock __bss_decrypted;
static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
static struct pvclock_vsyscall_time_info *hvclock_mem;

static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
{
	return &this_cpu_read(hv_clock_per_cpu)->pvti;
}

static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
{
	return this_cpu_read(hv_clock_per_cpu);
}

/*
 * The wallclock is the time of day when we booted. Since then, some time may
 * have elapsed since the hypervisor wrote the data. So we try to account for
 * that with system time
 */
static void kvm_get_wallclock(struct timespec64 *now)
{
	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
	preempt_disable();
	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
	preempt_enable();
}

static int kvm_set_wallclock(const struct timespec64 *now)
{
	return -ENODEV;
}

static u64 kvm_clock_read(void)
{
	u64 ret;

	preempt_disable_notrace();
	ret = pvclock_clocksource_read(this_cpu_pvti());
	preempt_enable_notrace();
	return ret;
}

static u64 kvm_clock_get_cycles(struct clocksource *cs)
{
	return kvm_clock_read();
}

static u64 kvm_sched_clock_read(void)
{
	return kvm_clock_read() - kvm_sched_clock_offset;
}

static inline void kvm_sched_clock_init(bool stable)
{
	if (!stable)
		clear_sched_clock_stable();
	kvm_sched_clock_offset = kvm_clock_read();
	paravirt_set_sched_clock(kvm_sched_clock_read);

	pr_info("kvm-clock: using sched offset of %llu cycles",
		kvm_sched_clock_offset);

	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
		sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
}

/*
 * If we don't do that, there is the possibility that the guest
 * will calibrate under heavy load - thus, getting a lower lpj -
 * and execute the delays themselves without load. This is wrong,
 * because no delay loop can finish beforehand.
 * Any heuristics is subject to fail, because ultimately, a large
 * poll of guests can be running and trouble each other. So we preset
 * lpj here
 */
static unsigned long kvm_get_tsc_khz(void)
{
	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
	return pvclock_tsc_khz(this_cpu_pvti());
}

static void __init kvm_get_preset_lpj(void)
{
	unsigned long khz;
	u64 lpj;

	khz = kvm_get_tsc_khz();

	lpj = ((u64)khz * 1000);
	do_div(lpj, HZ);
	preset_lpj = lpj;
}

bool kvm_check_and_clear_guest_paused(void)
{
	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
	bool ret = false;

	if (!src)
		return ret;

	if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
		src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
		pvclock_touch_watchdogs();
		ret = true;
	}
	return ret;
}

static int kvm_cs_enable(struct clocksource *cs)
{
	vclocks_set_used(VDSO_CLOCKMODE_PVCLOCK);
	return 0;
}

struct clocksource kvm_clock = {
	.name	= "kvm-clock",
	.read	= kvm_clock_get_cycles,
	.rating	= 400,
	.mask	= CLOCKSOURCE_MASK(64),
	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
	.enable	= kvm_cs_enable,
};
EXPORT_SYMBOL_GPL(kvm_clock);

static void kvm_register_clock(char *txt)
{
	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
	u64 pa;

	if (!src)
		return;

	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
	wrmsrl(msr_kvm_system_time, pa);
	pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
}

static void kvm_save_sched_clock_state(void)
{
}

static void kvm_restore_sched_clock_state(void)
{
	kvm_register_clock("primary cpu clock, resume");
}

#ifdef CONFIG_X86_LOCAL_APIC
static void kvm_setup_secondary_clock(void)
{
	kvm_register_clock("secondary cpu clock");
}
#endif

/*
 * After the clock is registered, the host will keep writing to the
 * registered memory location. If the guest happens to shutdown, this memory
 * won't be valid. In cases like kexec, in which you install a new kernel, this
 * means a random memory location will be kept being written. So before any
 * kind of shutdown from our side, we unregister the clock by writing anything
 * that does not have the 'enable' bit set in the msr
 */
#ifdef CONFIG_KEXEC_CORE
static void kvm_crash_shutdown(struct pt_regs *regs)
{
	native_write_msr(msr_kvm_system_time, 0, 0);
	kvm_disable_steal_time();
	native_machine_crash_shutdown(regs);
}
#endif

static void kvm_shutdown(void)
{
	native_write_msr(msr_kvm_system_time, 0, 0);
	kvm_disable_steal_time();
	native_machine_shutdown();
}

static void __init kvmclock_init_mem(void)
{
	unsigned long ncpus;
	unsigned int order;
	struct page *p;
	int r;

	if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus())
		return;

	ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE;
	order = get_order(ncpus * sizeof(*hvclock_mem));

	p = alloc_pages(GFP_KERNEL, order);
	if (!p) {
		pr_warn("%s: failed to alloc %d pages", __func__, (1U << order));
		return;
	}

	hvclock_mem = page_address(p);

	/*
	 * hvclock is shared between the guest and the hypervisor, must
	 * be mapped decrypted.
	 */
	if (sev_active()) {
		r = set_memory_decrypted((unsigned long) hvclock_mem,
					 1UL << order);
		if (r) {
			__free_pages(p, order);
			hvclock_mem = NULL;
			pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n");
			return;
		}
	}

	memset(hvclock_mem, 0, PAGE_SIZE << order);
}

static int __init kvm_setup_vsyscall_timeinfo(void)
{
	kvmclock_init_mem();

#ifdef CONFIG_X86_64
	if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
		u8 flags;

		flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
		if (!(flags & PVCLOCK_TSC_STABLE_BIT))
			return 0;

		kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
	}
#endif

	return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);

static int kvmclock_setup_percpu(unsigned int cpu)
{
	struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);

	/*
	 * The per cpu area setup replicates CPU0 data to all cpu
	 * pointers. So carefully check. CPU0 has been set up in init
	 * already.
	 */
	if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
		return 0;

	/* Use the static page for the first CPUs, allocate otherwise */
	if (cpu < HVC_BOOT_ARRAY_SIZE)
		p = &hv_clock_boot[cpu];
	else if (hvclock_mem)
		p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE;
	else
		return -ENOMEM;

	per_cpu(hv_clock_per_cpu, cpu) = p;
	return p ? 0 : -ENOMEM;
}

void __init kvmclock_init(void)
{
	u8 flags;

	if (!kvm_para_available() || !kvmclock)
		return;

	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
		return;
	}

	if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
			      kvmclock_setup_percpu, NULL) < 0) {
		return;
	}

	pr_info("kvm-clock: Using msrs %x and %x",
		msr_kvm_system_time, msr_kvm_wall_clock);

	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
	kvm_register_clock("primary cpu clock");
	pvclock_set_pvti_cpu0_va(hv_clock_boot);

	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);

	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);

	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
	x86_platform.get_wallclock = kvm_get_wallclock;
	x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
#endif
	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
	machine_ops.shutdown  = kvm_shutdown;
#ifdef CONFIG_KEXEC_CORE
	machine_ops.crash_shutdown  = kvm_crash_shutdown;
#endif
	kvm_get_preset_lpj();

	/*
	 * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate
	 * with P/T states and does not stop in deep C-states.
	 *
	 * Invariant TSC exposed by host means kvmclock is not necessary:
	 * can use TSC as clocksource.
	 *
	 */
	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
	    !check_tsc_unstable())
		kvm_clock.rating = 299;

	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
	pv_info.name = "KVM";
}