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
|
/*
* QEMU fw_cfg helpers (X86 specific)
*
* Copyright (c) 2019 Red Hat, Inc.
*
* Author:
* Philippe Mathieu-Daudé <philmd@redhat.com>
*
* SPDX-License-Identifier: GPL-2.0-or-later
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "system/numa.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/aml-build.h"
#include "hw/firmware/smbios.h"
#include "hw/i386/fw_cfg.h"
#include "hw/timer/hpet.h"
#include "hw/nvram/fw_cfg.h"
#include "e820_memory_layout.h"
#include "kvm/kvm_i386.h"
#include "qapi/error.h"
#include CONFIG_DEVICES
#include "target/i386/cpu.h"
struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX};
const char *fw_cfg_arch_key_name(uint16_t key)
{
static const struct {
uint16_t key;
const char *name;
} fw_cfg_arch_wellknown_keys[] = {
{FW_CFG_ACPI_TABLES, "acpi_tables"},
{FW_CFG_SMBIOS_ENTRIES, "smbios_entries"},
{FW_CFG_IRQ0_OVERRIDE, "irq0_override"},
{FW_CFG_HPET, "hpet"},
};
for (size_t i = 0; i < ARRAY_SIZE(fw_cfg_arch_wellknown_keys); i++) {
if (fw_cfg_arch_wellknown_keys[i].key == key) {
return fw_cfg_arch_wellknown_keys[i].name;
}
}
return NULL;
}
/* Add etc/e820 late, once all regions should be present */
void fw_cfg_add_e820(FWCfgState *fw_cfg)
{
struct e820_entry *table;
int nr_e820 = e820_get_table(&table);
fw_cfg_add_file(fw_cfg, "etc/e820", table, nr_e820 * sizeof(*table));
}
void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
SmbiosEntryPointType ep_type)
{
#ifdef CONFIG_SMBIOS
uint8_t *smbios_tables, *smbios_anchor;
size_t smbios_tables_len, smbios_anchor_len;
struct smbios_phys_mem_area *mem_array;
unsigned i, array_count;
MachineState *ms = MACHINE(pcms);
PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
MachineClass *mc = MACHINE_GET_CLASS(pcms);
X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
int nr_e820;
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name);
}
/* tell smbios about cpuid version and features */
smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
if (pcmc->smbios_legacy_mode) {
smbios_tables = smbios_get_table_legacy(&smbios_tables_len,
&error_fatal);
fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
smbios_tables, smbios_tables_len);
return;
}
/* build the array of physical mem area from e820 table */
nr_e820 = e820_get_table(NULL);
mem_array = g_malloc0(sizeof(*mem_array) * nr_e820);
for (i = 0, array_count = 0; i < nr_e820; i++) {
uint64_t addr, len;
if (e820_get_entry(i, E820_RAM, &addr, &len)) {
mem_array[array_count].address = addr;
mem_array[array_count].length = len;
array_count++;
}
}
smbios_get_tables(ms, ep_type, mem_array, array_count,
&smbios_tables, &smbios_tables_len,
&smbios_anchor, &smbios_anchor_len,
&error_fatal);
g_free(mem_array);
if (smbios_anchor) {
fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables",
smbios_tables, smbios_tables_len);
fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor",
smbios_anchor, smbios_anchor_len);
}
#endif
}
FWCfgState *fw_cfg_arch_create(MachineState *ms,
uint16_t boot_cpus,
uint16_t apic_id_limit)
{
FWCfgState *fw_cfg;
uint64_t *numa_fw_cfg;
int i;
MachineClass *mc = MACHINE_GET_CLASS(ms);
const CPUArchIdList *cpus = mc->possible_cpu_arch_ids(ms);
int nb_numa_nodes = ms->numa_state->num_nodes;
fw_cfg = fw_cfg_init_io_dma(FW_CFG_IO_BASE, FW_CFG_IO_BASE + 4,
&address_space_memory);
fw_cfg_add_i16(fw_cfg, FW_CFG_NB_CPUS, boot_cpus);
/* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:
*
* For machine types prior to 1.8, SeaBIOS needs FW_CFG_MAX_CPUS for
* building MPTable, ACPI MADT, ACPI CPU hotplug and ACPI SRAT table,
* that tables are based on xAPIC ID and QEMU<->SeaBIOS interface
* for CPU hotplug also uses APIC ID and not "CPU index".
* This means that FW_CFG_MAX_CPUS is not the "maximum number of CPUs",
* but the "limit to the APIC ID values SeaBIOS may see".
*
* So for compatibility reasons with old BIOSes we are stuck with
* "etc/max-cpus" actually being apic_id_limit
*/
fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, apic_id_limit);
fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, ms->ram_size);
#ifdef CONFIG_ACPI
fw_cfg_add_bytes(fw_cfg, FW_CFG_ACPI_TABLES,
acpi_tables, acpi_tables_len);
#endif
fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, 1);
fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));
/* allocate memory for the NUMA channel: one (64bit) word for the number
* of nodes, one word for each VCPU->node and one word for each node to
* hold the amount of memory.
*/
numa_fw_cfg = g_new0(uint64_t, 1 + apic_id_limit + nb_numa_nodes);
numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
for (i = 0; i < cpus->len; i++) {
unsigned int apic_id = cpus->cpus[i].arch_id;
assert(apic_id < apic_id_limit);
numa_fw_cfg[apic_id + 1] = cpu_to_le64(cpus->cpus[i].props.node_id);
}
for (i = 0; i < nb_numa_nodes; i++) {
numa_fw_cfg[apic_id_limit + 1 + i] =
cpu_to_le64(ms->numa_state->nodes[i].node_mem);
}
fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
(1 + apic_id_limit + nb_numa_nodes) *
sizeof(*numa_fw_cfg));
return fw_cfg;
}
void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg)
{
X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
CPUX86State *env = &cpu->env;
uint32_t unused, ebx, ecx, edx;
uint64_t feature_control_bits = 0;
uint64_t *val;
cpu_x86_cpuid(env, 1, 0, &unused, &unused, &ecx, &edx);
if (ecx & CPUID_EXT_VMX) {
feature_control_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
}
if ((edx & (CPUID_EXT2_MCE | CPUID_EXT2_MCA)) ==
(CPUID_EXT2_MCE | CPUID_EXT2_MCA) &&
(env->mcg_cap & MCG_LMCE_P)) {
feature_control_bits |= FEATURE_CONTROL_LMCE;
}
if (env->cpuid_level >= 7) {
cpu_x86_cpuid(env, 0x7, 0, &unused, &ebx, &ecx, &unused);
if (ebx & CPUID_7_0_EBX_SGX) {
feature_control_bits |= FEATURE_CONTROL_SGX;
}
if (ecx & CPUID_7_0_ECX_SGX_LC) {
feature_control_bits |= FEATURE_CONTROL_SGX_LC;
}
}
if (!feature_control_bits) {
return;
}
val = g_malloc(sizeof(*val));
*val = cpu_to_le64(feature_control_bits | FEATURE_CONTROL_LOCKED);
fw_cfg_add_file(fw_cfg, "etc/msr_feature_control", val, sizeof(*val));
}
#ifdef CONFIG_ACPI
void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg)
{
/*
* when using port i/o, the 8-bit data register *always* overlaps
* with half of the 16-bit control register. Hence, the total size
* of the i/o region used is FW_CFG_CTL_SIZE; when using DMA, the
* DMA control register is located at FW_CFG_DMA_IO_BASE + 4
*/
Object *obj = OBJECT(fw_cfg);
uint8_t io_size = object_property_get_bool(obj, "dma_enabled", NULL) ?
ROUND_UP(FW_CFG_CTL_SIZE, 4) + sizeof(dma_addr_t) :
FW_CFG_CTL_SIZE;
Aml *dev = aml_device("FWCF");
Aml *crs = aml_resource_template();
aml_append(dev, aml_name_decl("_HID", aml_string("QEMU0002")));
/* device present, functioning, decoding, not shown in UI */
aml_append(dev, aml_name_decl("_STA", aml_int(0xB)));
aml_append(crs,
aml_io(AML_DECODE16, FW_CFG_IO_BASE, FW_CFG_IO_BASE, 0x01, io_size));
aml_append(dev, aml_name_decl("_CRS", crs));
aml_append(scope, dev);
}
#endif
|
