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
|
/******************************************************************************
* arch/x86/x86_64/mm.c
*
* Modifications to Linux original are copyright (c) 2004, K A Fraser tr 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., 59
* Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <xen/config.h>
#include <xen/lib.h>
#include <xen/init.h>
#include <xen/mm.h>
#include <xen/sched.h>
#include <asm/asm_defns.h>
#include <asm/page.h>
#include <asm/flushtlb.h>
#include <asm/fixmap.h>
#include <asm/msr.h>
struct pfn_info *alloc_xen_pagetable(void)
{
extern int early_boot;
unsigned long p;
if ( !early_boot )
return alloc_domheap_page(NULL);
p = alloc_boot_pages(PAGE_SIZE, PAGE_SIZE);
return ((p == 0) ? NULL : phys_to_page(p));
}
void free_xen_pagetable(struct pfn_info *pg)
{
free_domheap_page(pg);
}
l2_pgentry_t *virt_to_xen_l2e(unsigned long v)
{
l4_pgentry_t *pl4e;
l3_pgentry_t *pl3e;
l2_pgentry_t *pl2e;
pl4e = &idle_pg_table[l4_table_offset(v)];
if ( !(l4e_get_flags(*pl4e) & _PAGE_PRESENT) )
{
pl3e = page_to_virt(alloc_xen_pagetable());
clear_page(pl3e);
*pl4e = l4e_from_paddr(__pa(pl3e), __PAGE_HYPERVISOR);
}
pl3e = l4e_to_l3e(*pl4e) + l3_table_offset(v);
if ( !(l3e_get_flags(*pl3e) & _PAGE_PRESENT) )
{
pl2e = page_to_virt(alloc_xen_pagetable());
clear_page(pl2e);
*pl3e = l3e_from_paddr(__pa(pl2e), __PAGE_HYPERVISOR);
}
pl2e = l3e_to_l2e(*pl3e) + l2_table_offset(v);
return pl2e;
}
void __init paging_init(void)
{
unsigned long i;
l3_pgentry_t *l3_ro_mpt;
l2_pgentry_t *l2_ro_mpt;
struct pfn_info *pg;
idle0_vcpu.arch.monitor_table = mk_pagetable(__pa(idle_pg_table));
/* Create user-accessible L2 directory to map the MPT for guests. */
l3_ro_mpt = (l3_pgentry_t *)alloc_xenheap_page();
clear_page(l3_ro_mpt);
idle_pg_table[l4_table_offset(RO_MPT_VIRT_START)] =
l4e_from_page(
virt_to_page(l3_ro_mpt), __PAGE_HYPERVISOR | _PAGE_USER);
l2_ro_mpt = (l2_pgentry_t *)alloc_xenheap_page();
clear_page(l2_ro_mpt);
l3_ro_mpt[l3_table_offset(RO_MPT_VIRT_START)] =
l3e_from_page(
virt_to_page(l2_ro_mpt), __PAGE_HYPERVISOR | _PAGE_USER);
l2_ro_mpt += l2_table_offset(RO_MPT_VIRT_START);
/*
* Allocate and map the machine-to-phys table.
* This also ensures L3 is present for fixmaps.
*/
for ( i = 0; i < max_page; i += ((1UL << L2_PAGETABLE_SHIFT) / 8) )
{
pg = alloc_domheap_pages(NULL, PAGETABLE_ORDER);
if ( pg == NULL )
panic("Not enough memory for m2p table\n");
map_pages_to_xen(
RDWR_MPT_VIRT_START + i*8, page_to_pfn(pg),
1UL << PAGETABLE_ORDER,
PAGE_HYPERVISOR);
memset((void *)(RDWR_MPT_VIRT_START + i*8), 0x55,
1UL << L2_PAGETABLE_SHIFT);
*l2_ro_mpt++ = l2e_from_page(
pg, _PAGE_GLOBAL|_PAGE_PSE|_PAGE_USER|_PAGE_PRESENT);
BUG_ON(((unsigned long)l2_ro_mpt & ~PAGE_MASK) == 0);
}
/* Set up linear page table mapping. */
idle_pg_table[l4_table_offset(LINEAR_PT_VIRT_START)] =
l4e_from_paddr(__pa(idle_pg_table), __PAGE_HYPERVISOR);
}
void __init zap_low_mappings(void)
{
idle_pg_table[0] = l4e_empty();
flush_tlb_all_pge();
}
void subarch_init_memory(struct domain *dom_xen)
{
unsigned long i, v, m2p_start_mfn;
l3_pgentry_t l3e;
l2_pgentry_t l2e;
/*
* We are rather picky about the layout of 'struct pfn_info'. The
* count_info and domain fields must be adjacent, as we perform atomic
* 64-bit operations on them.
*/
if ( (offsetof(struct pfn_info, u.inuse._domain) !=
(offsetof(struct pfn_info, count_info) + sizeof(u32))) )
{
printk("Weird pfn_info layout (%ld,%ld,%ld)\n",
offsetof(struct pfn_info, count_info),
offsetof(struct pfn_info, u.inuse._domain),
sizeof(struct pfn_info));
for ( ; ; ) ;
}
/* M2P table is mappable read-only by privileged domains. */
for ( v = RDWR_MPT_VIRT_START;
v != RDWR_MPT_VIRT_END;
v += 1 << L2_PAGETABLE_SHIFT )
{
l3e = l4e_to_l3e(idle_pg_table[l4_table_offset(v)])[
l3_table_offset(v)];
if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
continue;
l2e = l3e_to_l2e(l3e)[l2_table_offset(v)];
if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) )
continue;
m2p_start_mfn = l2e_get_pfn(l2e);
for ( i = 0; i < L1_PAGETABLE_ENTRIES; i++ )
{
frame_table[m2p_start_mfn+i].count_info = PGC_allocated | 1;
/* gdt to make sure it's only mapped read-only by non-privileged
domains. */
frame_table[m2p_start_mfn+i].u.inuse.type_info = PGT_gdt_page | 1;
page_set_owner(&frame_table[m2p_start_mfn+i], dom_xen);
}
}
}
long do_stack_switch(unsigned long ss, unsigned long esp)
{
if ( (ss & 3) != 3 )
return -EPERM;
current->arch.guest_context.kernel_ss = ss;
current->arch.guest_context.kernel_sp = esp;
return 0;
}
long do_set_segment_base(unsigned int which, unsigned long base)
{
struct vcpu *v = current;
long ret = 0;
switch ( which )
{
case SEGBASE_FS:
if ( wrmsr_user(MSR_FS_BASE, base, base>>32) )
ret = -EFAULT;
else
v->arch.guest_context.fs_base = base;
break;
case SEGBASE_GS_USER:
if ( wrmsr_user(MSR_SHADOW_GS_BASE, base, base>>32) )
ret = -EFAULT;
else
v->arch.guest_context.gs_base_user = base;
break;
case SEGBASE_GS_KERNEL:
if ( wrmsr_user(MSR_GS_BASE, base, base>>32) )
ret = -EFAULT;
else
v->arch.guest_context.gs_base_kernel = base;
break;
case SEGBASE_GS_USER_SEL:
__asm__ __volatile__ (
" swapgs \n"
"1: movl %k0,%%gs \n"
" "safe_swapgs" \n"
".section .fixup,\"ax\" \n"
"2: xorl %k0,%k0 \n"
" jmp 1b \n"
".previous \n"
".section __ex_table,\"a\"\n"
" .align 8 \n"
" .quad 1b,2b \n"
".previous "
: : "r" (base&0xffff) );
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
/* Returns TRUE if given descriptor is valid for GDT or LDT. */
int check_descriptor(struct desc_struct *d)
{
u32 a = d->a, b = d->b;
/* A not-present descriptor will always fault, so is safe. */
if ( !(b & _SEGMENT_P) )
goto good;
/* The guest can only safely be executed in ring 3. */
if ( (b & _SEGMENT_DPL) != _SEGMENT_DPL )
goto bad;
/* All code and data segments are okay. No base/limit checking. */
if ( (b & _SEGMENT_S) )
goto good;
/* Invalid type 0 is harmless. It is used for 2nd half of a call gate. */
if ( (b & _SEGMENT_TYPE) == 0x000 )
goto good;
/* Everything but a call gate is discarded here. */
if ( (b & _SEGMENT_TYPE) != 0xc00 )
goto bad;
/* Can't allow far jump to a Xen-private segment. */
if ( !VALID_CODESEL(a>>16) )
goto bad;
/* Reserved bits must be zero. */
if ( (b & 0xe0) != 0 )
goto bad;
good:
return 1;
bad:
return 0;
}
void memguard_guard_stack(void *p)
{
p = (void *)((unsigned long)p + PAGE_SIZE);
memguard_guard_range(p, 2 * PAGE_SIZE);
}
/*
* Local variables:
* mode: C
* c-set-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/
|
