summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/kvmclock.c
blob: b999f5e5b3bfd9dae4996798cebca7e1cf87cfaf (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
/*  KVM paravirtual clock driver. A clocksource implementation
    Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc.

    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, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
*/

#include <linux/clocksource.h>
#include <linux/kvm_para.h>
#include <asm/arch_hooks.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <linux/percpu.h>

#define KVM_SCALE 22

static int kvmclock = 1;

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

/* The hypervisor will put information about time periodically here */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field

static inline u64 kvm_get_delta(u64 last_tsc)
{
	int cpu = smp_processor_id();
	u64 delta = native_read_tsc() - last_tsc;
	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
}

static struct kvm_wall_clock wall_clock;
static cycle_t kvm_clock_read(void);
/*
 * 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
 */
unsigned long kvm_get_wallclock(void)
{
	u32 wc_sec, wc_nsec;
	u64 delta;
	struct timespec ts;
	int version, nsec;
	int low, high;

	low = (int)__pa(&wall_clock);
	high = ((u64)__pa(&wall_clock) >> 32);

	delta = kvm_clock_read();

	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
	do {
		version = wall_clock.wc_version;
		rmb();
		wc_sec = wall_clock.wc_sec;
		wc_nsec = wall_clock.wc_nsec;
		rmb();
	} while ((wall_clock.wc_version != version) || (version & 1));

	delta = kvm_clock_read() - delta;
	delta += wc_nsec;
	nsec = do_div(delta, NSEC_PER_SEC);
	set_normalized_timespec(&ts, wc_sec + delta, nsec);
	/*
	 * Of all mechanisms of time adjustment I've tested, this one
	 * was the champion!
	 */
	return ts.tv_sec + 1;
}

int kvm_set_wallclock(unsigned long now)
{
	return 0;
}

/*
 * This is our read_clock function. The host puts an tsc timestamp each time
 * it updates a new time. Without the tsc adjustment, we can have a situation
 * in which a vcpu starts to run earlier (smaller system_time), but probes
 * time later (compared to another vcpu), leading to backwards time
 */
static cycle_t kvm_clock_read(void)
{
	u64 last_tsc, now;
	int cpu;

	preempt_disable();
	cpu = smp_processor_id();

	last_tsc = get_clock(cpu, tsc_timestamp);
	now = get_clock(cpu, system_time);

	now += kvm_get_delta(last_tsc);
	preempt_enable();

	return now;
}
static struct clocksource kvm_clock = {
	.name = "kvm-clock",
	.read = kvm_clock_read,
	.rating = 400,
	.mask = CLOCKSOURCE_MASK(64),
	.mult = 1 << KVM_SCALE,
	.shift = KVM_SCALE,
	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};

static int kvm_register_clock(void)
{
	int cpu = smp_processor_id();
	int low, high;
	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);

	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
}

static void kvm_setup_secondary_clock(void)
{
	/*
	 * Now that the first cpu already had this clocksource initialized,
	 * we shouldn't fail.
	 */
	WARN_ON(kvm_register_clock());
	/* ok, done with our trickery, call native */
	setup_secondary_APIC_clock();
}

void __init kvmclock_init(void)
{
	if (!kvm_para_available())
		return;

	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
		if (kvm_register_clock())
			return;
		pv_time_ops.get_wallclock = kvm_get_wallclock;
		pv_time_ops.set_wallclock = kvm_set_wallclock;
		pv_time_ops.sched_clock = kvm_clock_read;
		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
		clocksource_register(&kvm_clock);
	}
}