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
|
#include <linux/cpu.h>
#include <linux/kexec.h>
#include <linux/memblock.h>
#include <xen/features.h>
#include <xen/events.h>
#include <xen/interface/memory.h>
#include <asm/cpu.h>
#include <asm/smp.h>
#include <asm/reboot.h>
#include <asm/setup.h>
#include <asm/hypervisor.h>
#include <asm/e820/api.h>
#include <asm/xen/cpuid.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/page.h>
#include "xen-ops.h"
#include "mmu.h"
#include "smp.h"
void __ref xen_hvm_init_shared_info(void)
{
struct xen_add_to_physmap xatp;
u64 pa;
if (HYPERVISOR_shared_info == &xen_dummy_shared_info) {
/*
* Search for a free page starting at 4kB physical address.
* Low memory is preferred to avoid an EPT large page split up
* by the mapping.
* Starting below X86_RESERVE_LOW (usually 64kB) is fine as
* the BIOS used for HVM guests is well behaved and won't
* clobber memory other than the first 4kB.
*/
for (pa = PAGE_SIZE;
!e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
memblock_is_reserved(pa);
pa += PAGE_SIZE)
;
memblock_reserve(pa, PAGE_SIZE);
HYPERVISOR_shared_info = __va(pa);
}
xatp.domid = DOMID_SELF;
xatp.idx = 0;
xatp.space = XENMAPSPACE_shared_info;
xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info);
if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
BUG();
}
static void __init init_hvm_pv_info(void)
{
int major, minor;
uint32_t eax, ebx, ecx, edx, base;
base = xen_cpuid_base();
eax = cpuid_eax(base + 1);
major = eax >> 16;
minor = eax & 0xffff;
printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
xen_domain_type = XEN_HVM_DOMAIN;
/* PVH set up hypercall page in xen_prepare_pvh(). */
if (xen_pvh_domain())
pv_info.name = "Xen PVH";
else {
u64 pfn;
uint32_t msr;
pv_info.name = "Xen HVM";
msr = cpuid_ebx(base + 2);
pfn = __pa(hypercall_page);
wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
}
xen_setup_features();
cpuid(base + 4, &eax, &ebx, &ecx, &edx);
if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
this_cpu_write(xen_vcpu_id, ebx);
else
this_cpu_write(xen_vcpu_id, smp_processor_id());
}
#ifdef CONFIG_KEXEC_CORE
static void xen_hvm_shutdown(void)
{
native_machine_shutdown();
if (kexec_in_progress)
xen_reboot(SHUTDOWN_soft_reset);
}
static void xen_hvm_crash_shutdown(struct pt_regs *regs)
{
native_machine_crash_shutdown(regs);
xen_reboot(SHUTDOWN_soft_reset);
}
#endif
static int xen_cpu_up_prepare_hvm(unsigned int cpu)
{
int rc = 0;
/*
* This can happen if CPU was offlined earlier and
* offlining timed out in common_cpu_die().
*/
if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
xen_smp_intr_free(cpu);
xen_uninit_lock_cpu(cpu);
}
if (cpu_acpi_id(cpu) != U32_MAX)
per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
else
per_cpu(xen_vcpu_id, cpu) = cpu;
rc = xen_vcpu_setup(cpu);
if (rc)
return rc;
if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
xen_setup_timer(cpu);
rc = xen_smp_intr_init(cpu);
if (rc) {
WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n",
cpu, rc);
}
return rc;
}
static int xen_cpu_dead_hvm(unsigned int cpu)
{
xen_smp_intr_free(cpu);
if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
xen_teardown_timer(cpu);
return 0;
}
static void __init xen_hvm_guest_init(void)
{
if (xen_pv_domain())
return;
init_hvm_pv_info();
xen_hvm_init_shared_info();
/*
* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
* page, we use it in the event channel upcall and in some pvclock
* related functions.
*/
xen_vcpu_info_reset(0);
xen_panic_handler_init();
if (xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
xen_hvm_smp_init();
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_hvm, xen_cpu_dead_hvm));
xen_unplug_emulated_devices();
x86_init.irqs.intr_init = xen_init_IRQ;
xen_hvm_init_time_ops();
xen_hvm_init_mmu_ops();
if (xen_pvh_domain())
machine_ops.emergency_restart = xen_emergency_restart;
#ifdef CONFIG_KEXEC_CORE
machine_ops.shutdown = xen_hvm_shutdown;
machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
#endif
}
static bool xen_nopv;
static __init int xen_parse_nopv(char *arg)
{
xen_nopv = true;
return 0;
}
early_param("xen_nopv", xen_parse_nopv);
bool xen_hvm_need_lapic(void)
{
if (xen_nopv)
return false;
if (xen_pv_domain())
return false;
if (!xen_hvm_domain())
return false;
if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
return false;
return true;
}
EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
static uint32_t __init xen_platform_hvm(void)
{
if (xen_pv_domain() || xen_nopv)
return 0;
return xen_cpuid_base();
}
const struct hypervisor_x86 x86_hyper_xen_hvm = {
.name = "Xen HVM",
.detect = xen_platform_hvm,
.init_platform = xen_hvm_guest_init,
.pin_vcpu = xen_pin_vcpu,
.x2apic_available = xen_x2apic_para_available,
};
EXPORT_SYMBOL(x86_hyper_xen_hvm);
|
