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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* KVM selftest s390x library code - CPU-related functions (page tables...)
*
* Copyright (C) 2019, Red Hat, Inc.
*/
#define _GNU_SOURCE /* for program_invocation_name */
#include "processor.h"
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
#define PAGES_PER_REGION 4
void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot)
{
vm_paddr_t paddr;
TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
vm->page_size);
if (vm->pgd_created)
return;
paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION,
KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot);
memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size);
vm->pgd = paddr;
vm->pgd_created = true;
}
/*
* Allocate 4 pages for a region/segment table (ri < 4), or one page for
* a page table (ri == 4). Returns a suitable region/segment table entry
* which points to the freshly allocated pages.
*/
static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot)
{
uint64_t taddr;
taddr = vm_phy_pages_alloc(vm, ri < 4 ? PAGES_PER_REGION : 1,
KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot);
memset(addr_gpa2hva(vm, taddr), 0xff, PAGES_PER_REGION * vm->page_size);
return (taddr & REGION_ENTRY_ORIGIN)
| (((4 - ri) << 2) & REGION_ENTRY_TYPE)
| ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH);
}
void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
uint32_t memslot)
{
int ri, idx;
uint64_t *entry;
TEST_ASSERT((gva % vm->page_size) == 0,
"Virtual address not on page boundary,\n"
" vaddr: 0x%lx vm->page_size: 0x%x",
gva, vm->page_size);
TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
(gva >> vm->page_shift)),
"Invalid virtual address, vaddr: 0x%lx",
gva);
TEST_ASSERT((gpa % vm->page_size) == 0,
"Physical address not on page boundary,\n"
" paddr: 0x%lx vm->page_size: 0x%x",
gva, vm->page_size);
TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn,
"Physical address beyond beyond maximum supported,\n"
" paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
gva, vm->max_gfn, vm->page_size);
/* Walk through region and segment tables */
entry = addr_gpa2hva(vm, vm->pgd);
for (ri = 1; ri <= 4; ri++) {
idx = (gva >> (64 - 11 * ri)) & 0x7ffu;
if (entry[idx] & REGION_ENTRY_INVALID)
entry[idx] = virt_alloc_region(vm, ri, memslot);
entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN);
}
/* Fill in page table entry */
idx = (gva >> 12) & 0x0ffu; /* page index */
if (!(entry[idx] & PAGE_INVALID))
fprintf(stderr,
"WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa);
entry[idx] = gpa;
}
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
int ri, idx;
uint64_t *entry;
TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
vm->page_size);
entry = addr_gpa2hva(vm, vm->pgd);
for (ri = 1; ri <= 4; ri++) {
idx = (gva >> (64 - 11 * ri)) & 0x7ffu;
TEST_ASSERT(!(entry[idx] & REGION_ENTRY_INVALID),
"No region mapping for vm virtual address 0x%lx",
gva);
entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN);
}
idx = (gva >> 12) & 0x0ffu; /* page index */
TEST_ASSERT(!(entry[idx] & PAGE_INVALID),
"No page mapping for vm virtual address 0x%lx", gva);
return (entry[idx] & ~0xffful) + (gva & 0xffful);
}
static void virt_dump_ptes(FILE *stream, struct kvm_vm *vm, uint8_t indent,
uint64_t ptea_start)
{
uint64_t *pte, ptea;
for (ptea = ptea_start; ptea < ptea_start + 0x100 * 8; ptea += 8) {
pte = addr_gpa2hva(vm, ptea);
if (*pte & PAGE_INVALID)
continue;
fprintf(stream, "%*spte @ 0x%lx: 0x%016lx\n",
indent, "", ptea, *pte);
}
}
static void virt_dump_region(FILE *stream, struct kvm_vm *vm, uint8_t indent,
uint64_t reg_tab_addr)
{
uint64_t addr, *entry;
for (addr = reg_tab_addr; addr < reg_tab_addr + 0x400 * 8; addr += 8) {
entry = addr_gpa2hva(vm, addr);
if (*entry & REGION_ENTRY_INVALID)
continue;
fprintf(stream, "%*srt%lde @ 0x%lx: 0x%016lx\n",
indent, "", 4 - ((*entry & REGION_ENTRY_TYPE) >> 2),
addr, *entry);
if (*entry & REGION_ENTRY_TYPE) {
virt_dump_region(stream, vm, indent + 2,
*entry & REGION_ENTRY_ORIGIN);
} else {
virt_dump_ptes(stream, vm, indent + 2,
*entry & REGION_ENTRY_ORIGIN);
}
}
}
void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
if (!vm->pgd_created)
return;
virt_dump_region(stream, vm, indent, vm->pgd);
}
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
void *guest_code)
{
/*
* The additional amount of pages required for the page tables is:
* 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ...
* which is definitely smaller than (n / 256) * 2.
*/
uint64_t extra_pg_pages = extra_mem_pages / 256 * 2;
struct kvm_vm *vm;
vm = vm_create(VM_MODE_DEFAULT,
DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
vm_vcpu_add_default(vm, vcpuid, guest_code);
return vm;
}
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
size_t stack_size = DEFAULT_STACK_PGS * getpagesize();
uint64_t stack_vaddr;
struct kvm_regs regs;
struct kvm_sregs sregs;
struct kvm_run *run;
TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
vm->page_size);
stack_vaddr = vm_vaddr_alloc(vm, stack_size,
DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
vm_vcpu_add(vm, vcpuid);
/* Setup guest registers */
vcpu_regs_get(vm, vcpuid, ®s);
regs.gprs[15] = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()) - 160;
vcpu_regs_set(vm, vcpuid, ®s);
vcpu_sregs_get(vm, vcpuid, &sregs);
sregs.crs[0] |= 0x00040000; /* Enable floating point regs */
sregs.crs[1] = vm->pgd | 0xf; /* Primary region table */
vcpu_sregs_set(vm, vcpuid, &sregs);
run = vcpu_state(vm, vcpuid);
run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */
run->psw_addr = (uintptr_t)guest_code;
}
void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
{
va_list ap;
struct kvm_regs regs;
int i;
TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
" num: %u\n",
num);
va_start(ap, num);
vcpu_regs_get(vm, vcpuid, ®s);
for (i = 0; i < num; i++)
regs.gprs[i + 2] = va_arg(ap, uint64_t);
vcpu_regs_set(vm, vcpuid, ®s);
va_end(ap);
}
void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
{
struct vcpu *vcpu = vm->vcpu_head;
fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
}
|
