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
|
/*
* Machine specific setup for xen
*
* Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/pm.h>
#include <asm/elf.h>
#include <asm/vdso.h>
#include <asm/e820.h>
#include <asm/setup.h>
#include <asm/acpi.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <xen/page.h>
#include <xen/interface/callback.h>
#include <xen/interface/physdev.h>
#include <xen/interface/memory.h>
#include <xen/features.h>
#include "xen-ops.h"
#include "vdso.h"
/* These are code, but not functions. Defined in entry.S */
extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
extern void xen_sysenter_target(void);
extern void xen_syscall_target(void);
extern void xen_syscall32_target(void);
static unsigned long __init xen_release_chunk(phys_addr_t start_addr, phys_addr_t end_addr)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
unsigned long start, end;
unsigned long len;
unsigned long pfn;
int ret;
start = PFN_UP(start_addr);
end = PFN_UP(end_addr);
if (end <= start)
return 0;
len = end - start;
set_xen_guest_handle(reservation.extent_start, &mfn_list[start]);
reservation.nr_extents = len;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
WARN(ret != (end - start), "Failed to release memory %lx-%lx err=%d\n",
start, end, ret);
for(pfn = start; pfn < end; pfn++)
set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
return len;
}
static unsigned long __init xen_return_unused_memory(const struct e820map *e820)
{
unsigned long last_end = 0;
unsigned long released = 0;
int i;
for (i = 0; i < e820->nr_map; i++) {
released += xen_release_chunk(last_end, e820->map[i].addr);
last_end = e820->map[i].addr + e820->map[i].size;
}
released += xen_release_chunk(last_end, PFN_PHYS(xen_start_info->nr_pages));
printk(KERN_INFO "released %ld pages of unused memory\n", released);
return released;
}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
unsigned long max_pfn = xen_start_info->nr_pages;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
e820.nr_map = 0;
e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
/*
* Even though this is normal, usable memory under Xen, reserve
* ISA memory anyway because too many things think they can poke
* about in there.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
/*
* Reserve Xen bits:
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
*/
reserve_early(__pa(xen_start_info->mfn_list),
__pa(xen_start_info->pt_base),
"XEN START INFO");
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
xen_return_unused_memory(&e820);
return "Xen";
}
static void xen_idle(void)
{
local_irq_disable();
if (need_resched())
local_irq_enable();
else {
current_thread_info()->status &= ~TS_POLLING;
smp_mb__after_clear_bit();
safe_halt();
current_thread_info()->status |= TS_POLLING;
}
}
/*
* Set the bit indicating "nosegneg" library variants should be used.
* We only need to bother in pure 32-bit mode; compat 32-bit processes
* can have un-truncated segments, so wrapping around is allowed.
*/
static void __init fiddle_vdso(void)
{
#ifdef CONFIG_X86_32
u32 *mask;
mask = VDSO32_SYMBOL(&vdso32_int80_start, NOTE_MASK);
*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
mask = VDSO32_SYMBOL(&vdso32_sysenter_start, NOTE_MASK);
*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
#endif
}
static __cpuinit int register_callback(unsigned type, const void *func)
{
struct callback_register callback = {
.type = type,
.address = XEN_CALLBACK(__KERNEL_CS, func),
.flags = CALLBACKF_mask_events,
};
return HYPERVISOR_callback_op(CALLBACKOP_register, &callback);
}
void __cpuinit xen_enable_sysenter(void)
{
int ret;
unsigned sysenter_feature;
#ifdef CONFIG_X86_32
sysenter_feature = X86_FEATURE_SEP;
#else
sysenter_feature = X86_FEATURE_SYSENTER32;
#endif
if (!boot_cpu_has(sysenter_feature))
return;
ret = register_callback(CALLBACKTYPE_sysenter, xen_sysenter_target);
if(ret != 0)
setup_clear_cpu_cap(sysenter_feature);
}
void __cpuinit xen_enable_syscall(void)
{
#ifdef CONFIG_X86_64
int ret;
ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
if (ret != 0) {
printk(KERN_ERR "Failed to set syscall callback: %d\n", ret);
/* Pretty fatal; 64-bit userspace has no other
mechanism for syscalls. */
}
if (boot_cpu_has(X86_FEATURE_SYSCALL32)) {
ret = register_callback(CALLBACKTYPE_syscall32,
xen_syscall32_target);
if (ret != 0)
setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
}
#endif /* CONFIG_X86_64 */
}
void __init xen_arch_setup(void)
{
struct physdev_set_iopl set_iopl;
int rc;
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
if (!xen_feature(XENFEAT_auto_translated_physmap))
HYPERVISOR_vm_assist(VMASST_CMD_enable,
VMASST_TYPE_pae_extended_cr3);
if (register_callback(CALLBACKTYPE_event, xen_hypervisor_callback) ||
register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))
BUG();
xen_enable_sysenter();
xen_enable_syscall();
set_iopl.iopl = 1;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
if (rc != 0)
printk(KERN_INFO "physdev_op failed %d\n", rc);
#ifdef CONFIG_ACPI
if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
disable_acpi();
}
#endif
memcpy(boot_command_line, xen_start_info->cmd_line,
MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ?
COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
pm_idle = xen_idle;
paravirt_disable_iospace();
fiddle_vdso();
}
|
