/src/qemu/hw/i386/x86-common.c
Line | Count | Source |
1 | | /* |
2 | | * Copyright (c) 2003-2004 Fabrice Bellard |
3 | | * Copyright (c) 2019, 2024 Red Hat, Inc. |
4 | | * |
5 | | * Permission is hereby granted, free of charge, to any person obtaining a copy |
6 | | * of this software and associated documentation files (the "Software"), to deal |
7 | | * in the Software without restriction, including without limitation the rights |
8 | | * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
9 | | * copies of the Software, and to permit persons to whom the Software is |
10 | | * furnished to do so, subject to the following conditions: |
11 | | * |
12 | | * The above copyright notice and this permission notice shall be included in |
13 | | * all copies or substantial portions of the Software. |
14 | | * |
15 | | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
16 | | * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
17 | | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
18 | | * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
19 | | * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
20 | | * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
21 | | * THE SOFTWARE. |
22 | | */ |
23 | | #include "qemu/osdep.h" |
24 | | #include "qemu/error-report.h" |
25 | | #include "qemu/cutils.h" |
26 | | #include "qemu/units.h" |
27 | | #include "qemu/datadir.h" |
28 | | #include "qapi/error.h" |
29 | | #include "system/numa.h" |
30 | | #include "system/system.h" |
31 | | #include "system/xen.h" |
32 | | #include "trace.h" |
33 | | |
34 | | #include "hw/i386/x86.h" |
35 | | #include "target/i386/cpu.h" |
36 | | #include "hw/rtc/mc146818rtc.h" |
37 | | #include "target/i386/sev.h" |
38 | | |
39 | | #include "hw/core/irq.h" |
40 | | #include "hw/core/loader.h" |
41 | | #include "multiboot.h" |
42 | | #include "elf.h" |
43 | | #include "standard-headers/asm-x86/bootparam.h" |
44 | | #include CONFIG_DEVICES |
45 | | #include "kvm/kvm_i386.h" |
46 | | #include "kvm/tdx.h" |
47 | | |
48 | | #include "exec/tswap.h" |
49 | | |
50 | | #ifdef CONFIG_XEN_EMU |
51 | | #include "hw/xen/xen.h" |
52 | | #include "hw/i386/kvm/xen_evtchn.h" |
53 | | #endif |
54 | | |
55 | | /* Physical Address of PVH entry point read from kernel ELF NOTE */ |
56 | | static size_t pvh_start_addr; |
57 | | |
58 | | static void x86_cpu_new(X86MachineState *x86ms, int64_t apic_id, Error **errp) |
59 | 63 | { |
60 | 63 | Object *cpu = object_new(MACHINE(x86ms)->cpu_type); |
61 | | |
62 | 63 | if (!object_property_set_uint(cpu, "apic-id", apic_id, errp)) { |
63 | 0 | goto out; |
64 | 0 | } |
65 | 63 | qdev_realize(DEVICE(cpu), NULL, errp); |
66 | | |
67 | 63 | out: |
68 | 63 | object_unref(cpu); |
69 | 63 | } |
70 | | |
71 | | void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version) |
72 | 63 | { |
73 | 63 | int i; |
74 | 63 | const CPUArchIdList *possible_cpus; |
75 | 63 | MachineState *ms = MACHINE(x86ms); |
76 | 63 | MachineClass *mc = MACHINE_GET_CLASS(x86ms); |
77 | | |
78 | 63 | x86_cpu_set_default_version(default_cpu_version); |
79 | | |
80 | | /* |
81 | | * Calculates the limit to CPU APIC ID values |
82 | | * |
83 | | * Limit for the APIC ID value, so that all |
84 | | * CPU APIC IDs are < x86ms->apic_id_limit. |
85 | | * |
86 | | * This is used for FW_CFG_MAX_CPUS. See comments on fw_cfg_arch_create(). |
87 | | */ |
88 | 63 | x86ms->apic_id_limit = x86_cpu_apic_id_from_index(x86ms, |
89 | 63 | ms->smp.max_cpus - 1) + 1; |
90 | | |
91 | | /* |
92 | | * Can we support APIC ID 255 or higher? With KVM, that requires |
93 | | * both in-kernel lapic and X2APIC userspace API. |
94 | | * |
95 | | * kvm_enabled() must go first to ensure that kvm_* references are |
96 | | * not emitted for the linker to consume (kvm_enabled() is |
97 | | * a literal `0` in configurations where kvm_* aren't defined) |
98 | | */ |
99 | 63 | if (kvm_enabled() && x86ms->apic_id_limit > 255 && |
100 | 0 | kvm_irqchip_in_kernel() && !kvm_enable_x2apic()) { |
101 | 0 | error_report("current -smp configuration requires kernel " |
102 | 0 | "irqchip and X2APIC API support."); |
103 | 0 | exit(EXIT_FAILURE); |
104 | 0 | } |
105 | | |
106 | 63 | if (kvm_enabled()) { |
107 | 0 | kvm_set_max_apic_id(x86ms->apic_id_limit); |
108 | 0 | } |
109 | | |
110 | 63 | if (!kvm_irqchip_in_kernel()) { |
111 | 63 | apic_set_max_apic_id(x86ms->apic_id_limit); |
112 | 63 | } |
113 | | |
114 | 63 | possible_cpus = mc->possible_cpu_arch_ids(ms); |
115 | 126 | for (i = 0; i < ms->smp.cpus; i++) { |
116 | 63 | x86_cpu_new(x86ms, possible_cpus->cpus[i].arch_id, &error_fatal); |
117 | 63 | } |
118 | 63 | } |
119 | | |
120 | | void x86_rtc_set_cpus_count(ISADevice *s, uint16_t cpus_count) |
121 | 63 | { |
122 | 63 | MC146818RtcState *rtc = MC146818_RTC(s); |
123 | | |
124 | 63 | if (cpus_count > 0xff) { |
125 | | /* |
126 | | * If the number of CPUs can't be represented in 8 bits, the |
127 | | * BIOS must use "FW_CFG_NB_CPUS". Set RTC field to 0 just |
128 | | * to make old BIOSes fail more predictably. |
129 | | */ |
130 | 0 | mc146818rtc_set_cmos_data(rtc, 0x5f, 0); |
131 | 63 | } else { |
132 | 63 | mc146818rtc_set_cmos_data(rtc, 0x5f, cpus_count - 1); |
133 | 63 | } |
134 | 63 | } |
135 | | |
136 | | static int x86_apic_cmp(const void *a, const void *b) |
137 | 126 | { |
138 | 126 | CPUArchId *apic_a = (CPUArchId *)a; |
139 | 126 | CPUArchId *apic_b = (CPUArchId *)b; |
140 | | |
141 | 126 | return apic_a->arch_id - apic_b->arch_id; |
142 | 126 | } |
143 | | |
144 | | /* |
145 | | * returns pointer to CPUArchId descriptor that matches CPU's apic_id |
146 | | * in ms->possible_cpus->cpus, if ms->possible_cpus->cpus has no |
147 | | * entry corresponding to CPU's apic_id returns NULL. |
148 | | */ |
149 | | static CPUArchId *x86_find_cpu_slot(MachineState *ms, uint32_t id, int *idx) |
150 | 126 | { |
151 | 126 | CPUArchId apic_id, *found_cpu; |
152 | | |
153 | 126 | apic_id.arch_id = id; |
154 | 126 | found_cpu = bsearch(&apic_id, ms->possible_cpus->cpus, |
155 | 126 | ms->possible_cpus->len, sizeof(*ms->possible_cpus->cpus), |
156 | 126 | x86_apic_cmp); |
157 | 126 | if (found_cpu && idx) { |
158 | 63 | *idx = found_cpu - ms->possible_cpus->cpus; |
159 | 63 | } |
160 | 126 | return found_cpu; |
161 | 126 | } |
162 | | |
163 | | void x86_cpu_plug(const HotplugHandler *hotplug_dev, |
164 | | DeviceState *dev, Error **errp) |
165 | 63 | { |
166 | 63 | CPUArchId *found_cpu; |
167 | 63 | Error *local_err = NULL; |
168 | 63 | X86CPU *cpu = X86_CPU(dev); |
169 | 63 | X86MachineState *x86ms = X86_MACHINE(hotplug_dev); |
170 | | |
171 | 63 | if (x86ms->acpi_dev) { |
172 | 0 | hotplug_handler_plug(x86ms->acpi_dev, dev, &local_err); |
173 | 0 | if (local_err) { |
174 | 0 | goto out; |
175 | 0 | } |
176 | 0 | } |
177 | | |
178 | | /* increment the number of CPUs */ |
179 | 63 | x86ms->boot_cpus++; |
180 | 63 | if (x86ms->rtc) { |
181 | 0 | x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); |
182 | 0 | } |
183 | 63 | if (x86ms->fw_cfg) { |
184 | 0 | fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); |
185 | 0 | } |
186 | | |
187 | | /* |
188 | | * Non-hotplugged CPUs get their SMM cpu address space initialized in |
189 | | * machine init done notifier: register_smram_listener(). |
190 | | * |
191 | | * We need initialize the SMM cpu address space for the hotplugged CPU |
192 | | * specifically. |
193 | | */ |
194 | 63 | if (kvm_enabled() && dev->hotplugged && x86_machine_is_smm_enabled(x86ms)) { |
195 | 0 | kvm_smm_cpu_address_space_init(cpu); |
196 | 0 | } |
197 | | |
198 | 63 | found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); |
199 | 63 | found_cpu->cpu = CPU(dev); |
200 | 63 | out: |
201 | 63 | error_propagate(errp, local_err); |
202 | 63 | } |
203 | | |
204 | | void x86_cpu_unplug_request_cb(const HotplugHandler *hotplug_dev, |
205 | | DeviceState *dev, Error **errp) |
206 | 0 | { |
207 | 0 | int idx = -1; |
208 | 0 | X86CPU *cpu = X86_CPU(dev); |
209 | 0 | X86MachineState *x86ms = X86_MACHINE(hotplug_dev); |
210 | |
|
211 | 0 | if (!x86ms->acpi_dev) { |
212 | 0 | error_setg(errp, "CPU hot unplug not supported without ACPI"); |
213 | 0 | return; |
214 | 0 | } |
215 | | |
216 | 0 | x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); |
217 | 0 | assert(idx != -1); |
218 | 0 | if (idx == 0) { |
219 | 0 | error_setg(errp, "Boot CPU is unpluggable"); |
220 | 0 | return; |
221 | 0 | } |
222 | | |
223 | 0 | hotplug_handler_unplug_request(x86ms->acpi_dev, dev, |
224 | 0 | errp); |
225 | 0 | } |
226 | | |
227 | | void x86_cpu_unplug_cb(const HotplugHandler *hotplug_dev, |
228 | | DeviceState *dev, Error **errp) |
229 | 0 | { |
230 | 0 | CPUArchId *found_cpu; |
231 | 0 | Error *local_err = NULL; |
232 | 0 | X86CPU *cpu = X86_CPU(dev); |
233 | 0 | X86MachineState *x86ms = X86_MACHINE(hotplug_dev); |
234 | |
|
235 | 0 | hotplug_handler_unplug(x86ms->acpi_dev, dev, &local_err); |
236 | 0 | if (local_err) { |
237 | 0 | goto out; |
238 | 0 | } |
239 | | |
240 | 0 | found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); |
241 | 0 | found_cpu->cpu = NULL; |
242 | 0 | qdev_unrealize(dev); |
243 | | |
244 | | /* decrement the number of CPUs */ |
245 | 0 | x86ms->boot_cpus--; |
246 | | /* Update the number of CPUs in CMOS */ |
247 | 0 | x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); |
248 | 0 | fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); |
249 | 0 | out: |
250 | 0 | error_propagate(errp, local_err); |
251 | 0 | } |
252 | | |
253 | | void x86_cpu_pre_plug(const HotplugHandler *hotplug_dev, |
254 | | DeviceState *dev, Error **errp) |
255 | 63 | { |
256 | 63 | int idx; |
257 | 63 | CPUState *cs; |
258 | 63 | CPUArchId *cpu_slot; |
259 | 63 | X86CPUTopoIDs topo_ids; |
260 | 63 | X86CPU *cpu = X86_CPU(dev); |
261 | 63 | CPUX86State *env = &cpu->env; |
262 | 63 | MachineState *ms = MACHINE(hotplug_dev); |
263 | 63 | X86MachineState *x86ms = X86_MACHINE(hotplug_dev); |
264 | 63 | X86CPUTopoInfo *topo_info = &env->topo_info; |
265 | | |
266 | 63 | if (!object_dynamic_cast(OBJECT(cpu), ms->cpu_type)) { |
267 | 0 | error_setg(errp, "Invalid CPU type, expected cpu type: '%s'", |
268 | 0 | ms->cpu_type); |
269 | 0 | return; |
270 | 0 | } |
271 | | |
272 | 63 | if (x86ms->acpi_dev) { |
273 | 0 | Error *local_err = NULL; |
274 | |
|
275 | 0 | hotplug_handler_pre_plug(HOTPLUG_HANDLER(x86ms->acpi_dev), dev, |
276 | 0 | &local_err); |
277 | 0 | if (local_err) { |
278 | 0 | error_propagate(errp, local_err); |
279 | 0 | return; |
280 | 0 | } |
281 | 0 | } |
282 | | |
283 | 63 | init_topo_info(topo_info, x86ms); |
284 | | |
285 | 63 | if (ms->smp.modules > 1) { |
286 | 0 | set_bit(CPU_TOPOLOGY_LEVEL_MODULE, env->avail_cpu_topo); |
287 | 0 | } |
288 | | |
289 | 63 | if (ms->smp.dies > 1) { |
290 | 0 | set_bit(CPU_TOPOLOGY_LEVEL_DIE, env->avail_cpu_topo); |
291 | 0 | } |
292 | | |
293 | | /* |
294 | | * If APIC ID is not set, |
295 | | * set it based on socket/die/module/core/thread properties. |
296 | | */ |
297 | 63 | if (cpu->apic_id == UNASSIGNED_APIC_ID) { |
298 | | /* |
299 | | * die-id was optional in QEMU 4.0 and older, so keep it optional |
300 | | * if there's only one die per socket. |
301 | | */ |
302 | 0 | if (cpu->die_id < 0 && ms->smp.dies == 1) { |
303 | 0 | cpu->die_id = 0; |
304 | 0 | } |
305 | | |
306 | | /* |
307 | | * module-id was optional in QEMU 9.0 and older, so keep it optional |
308 | | * if there's only one module per die. |
309 | | */ |
310 | 0 | if (cpu->module_id < 0 && ms->smp.modules == 1) { |
311 | 0 | cpu->module_id = 0; |
312 | 0 | } |
313 | |
|
314 | 0 | if (cpu->socket_id < 0) { |
315 | 0 | error_setg(errp, "CPU socket-id is not set"); |
316 | 0 | return; |
317 | 0 | } else if (cpu->socket_id > ms->smp.sockets - 1) { |
318 | 0 | error_setg(errp, "Invalid CPU socket-id: %u must be in range 0:%u", |
319 | 0 | cpu->socket_id, ms->smp.sockets - 1); |
320 | 0 | return; |
321 | 0 | } |
322 | 0 | if (cpu->die_id < 0) { |
323 | 0 | error_setg(errp, "CPU die-id is not set"); |
324 | 0 | return; |
325 | 0 | } else if (cpu->die_id > ms->smp.dies - 1) { |
326 | 0 | error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", |
327 | 0 | cpu->die_id, ms->smp.dies - 1); |
328 | 0 | return; |
329 | 0 | } |
330 | 0 | if (cpu->module_id < 0) { |
331 | 0 | error_setg(errp, "CPU module-id is not set"); |
332 | 0 | return; |
333 | 0 | } else if (cpu->module_id > ms->smp.modules - 1) { |
334 | 0 | error_setg(errp, "Invalid CPU module-id: %u must be in range 0:%u", |
335 | 0 | cpu->module_id, ms->smp.modules - 1); |
336 | 0 | return; |
337 | 0 | } |
338 | 0 | if (cpu->core_id < 0) { |
339 | 0 | error_setg(errp, "CPU core-id is not set"); |
340 | 0 | return; |
341 | 0 | } else if (cpu->core_id > (ms->smp.cores - 1)) { |
342 | 0 | error_setg(errp, "Invalid CPU core-id: %u must be in range 0:%u", |
343 | 0 | cpu->core_id, ms->smp.cores - 1); |
344 | 0 | return; |
345 | 0 | } |
346 | 0 | if (cpu->thread_id < 0) { |
347 | 0 | error_setg(errp, "CPU thread-id is not set"); |
348 | 0 | return; |
349 | 0 | } else if (cpu->thread_id > (ms->smp.threads - 1)) { |
350 | 0 | error_setg(errp, "Invalid CPU thread-id: %u must be in range 0:%u", |
351 | 0 | cpu->thread_id, ms->smp.threads - 1); |
352 | 0 | return; |
353 | 0 | } |
354 | | |
355 | 0 | topo_ids.pkg_id = cpu->socket_id; |
356 | 0 | topo_ids.die_id = cpu->die_id; |
357 | 0 | topo_ids.module_id = cpu->module_id; |
358 | 0 | topo_ids.core_id = cpu->core_id; |
359 | 0 | topo_ids.smt_id = cpu->thread_id; |
360 | 0 | cpu->apic_id = x86_apicid_from_topo_ids(topo_info, &topo_ids); |
361 | 0 | } |
362 | | |
363 | 63 | cpu_slot = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); |
364 | 63 | if (!cpu_slot) { |
365 | 0 | x86_topo_ids_from_apicid(cpu->apic_id, topo_info, &topo_ids); |
366 | |
|
367 | 0 | error_setg(errp, |
368 | 0 | "Invalid CPU [socket: %u, die: %u, module: %u, core: %u, thread: %u]" |
369 | 0 | " with APIC ID %" PRIu32 ", valid index range 0:%d", |
370 | 0 | topo_ids.pkg_id, topo_ids.die_id, topo_ids.module_id, |
371 | 0 | topo_ids.core_id, topo_ids.smt_id, cpu->apic_id, |
372 | 0 | ms->possible_cpus->len - 1); |
373 | 0 | return; |
374 | 0 | } |
375 | | |
376 | 63 | if (cpu_slot->cpu) { |
377 | 0 | error_setg(errp, "CPU[%d] with APIC ID %" PRIu32 " exists", |
378 | 0 | idx, cpu->apic_id); |
379 | 0 | return; |
380 | 0 | } |
381 | | |
382 | | /* if 'address' properties socket-id/core-id/thread-id are not set, set them |
383 | | * so that machine_query_hotpluggable_cpus would show correct values |
384 | | */ |
385 | | /* TODO: move socket_id/core_id/thread_id checks into x86_cpu_realizefn() |
386 | | * once -smp refactoring is complete and there will be CPU private |
387 | | * CPUState::nr_cores and CPUState::nr_threads fields instead of globals */ |
388 | 63 | x86_topo_ids_from_apicid(cpu->apic_id, topo_info, &topo_ids); |
389 | 63 | if (cpu->socket_id != -1 && cpu->socket_id != topo_ids.pkg_id) { |
390 | 0 | error_setg(errp, "property socket-id: %u doesn't match set apic-id:" |
391 | 0 | " 0x%x (socket-id: %u)", cpu->socket_id, cpu->apic_id, |
392 | 0 | topo_ids.pkg_id); |
393 | 0 | return; |
394 | 0 | } |
395 | 63 | cpu->socket_id = topo_ids.pkg_id; |
396 | | |
397 | 63 | if (cpu->die_id != -1 && cpu->die_id != topo_ids.die_id) { |
398 | 0 | error_setg(errp, "property die-id: %u doesn't match set apic-id:" |
399 | 0 | " 0x%x (die-id: %u)", cpu->die_id, cpu->apic_id, topo_ids.die_id); |
400 | 0 | return; |
401 | 0 | } |
402 | 63 | cpu->die_id = topo_ids.die_id; |
403 | | |
404 | 63 | if (cpu->module_id != -1 && cpu->module_id != topo_ids.module_id) { |
405 | 0 | error_setg(errp, "property module-id: %u doesn't match set apic-id:" |
406 | 0 | " 0x%x (module-id: %u)", cpu->module_id, cpu->apic_id, |
407 | 0 | topo_ids.module_id); |
408 | 0 | return; |
409 | 0 | } |
410 | 63 | cpu->module_id = topo_ids.module_id; |
411 | | |
412 | 63 | if (cpu->core_id != -1 && cpu->core_id != topo_ids.core_id) { |
413 | 0 | error_setg(errp, "property core-id: %u doesn't match set apic-id:" |
414 | 0 | " 0x%x (core-id: %u)", cpu->core_id, cpu->apic_id, |
415 | 0 | topo_ids.core_id); |
416 | 0 | return; |
417 | 0 | } |
418 | 63 | cpu->core_id = topo_ids.core_id; |
419 | | |
420 | 63 | if (cpu->thread_id != -1 && cpu->thread_id != topo_ids.smt_id) { |
421 | 0 | error_setg(errp, "property thread-id: %u doesn't match set apic-id:" |
422 | 0 | " 0x%x (thread-id: %u)", cpu->thread_id, cpu->apic_id, |
423 | 0 | topo_ids.smt_id); |
424 | 0 | return; |
425 | 0 | } |
426 | 63 | cpu->thread_id = topo_ids.smt_id; |
427 | | |
428 | | /* |
429 | | * kvm_enabled() must go first to ensure that kvm_* references are |
430 | | * not emitted for the linker to consume (kvm_enabled() is |
431 | | * a literal `0` in configurations where kvm_* aren't defined) |
432 | | */ |
433 | 63 | if (kvm_enabled() && hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX) && |
434 | 0 | !kvm_hv_vpindex_settable()) { |
435 | 0 | error_setg(errp, "kernel doesn't allow setting HyperV VP_INDEX"); |
436 | 0 | return; |
437 | 0 | } |
438 | | |
439 | 63 | cs = CPU(cpu); |
440 | 63 | cs->cpu_index = idx; |
441 | | |
442 | 63 | numa_cpu_pre_plug(cpu_slot, dev, errp); |
443 | 63 | } |
444 | | |
445 | | static long get_file_size(FILE *f) |
446 | 0 | { |
447 | 0 | long where, size; |
448 | | |
449 | | /* XXX: on Unix systems, using fstat() probably makes more sense */ |
450 | |
|
451 | 0 | where = ftell(f); |
452 | 0 | fseek(f, 0, SEEK_END); |
453 | 0 | size = ftell(f); |
454 | 0 | fseek(f, where, SEEK_SET); |
455 | |
|
456 | 0 | return size; |
457 | 0 | } |
458 | | |
459 | | void gsi_handler(void *opaque, int n, int level) |
460 | 31.5M | { |
461 | 31.5M | GSIState *s = opaque; |
462 | 31.5M | bool bypass_ioapic = false; |
463 | | |
464 | 31.5M | trace_x86_gsi_interrupt(n, level); |
465 | | |
466 | 31.5M | #ifdef CONFIG_XEN_EMU |
467 | | /* |
468 | | * Xen delivers the GSI to the Legacy PIC (not that Legacy PIC |
469 | | * routing actually works properly under Xen). And then to |
470 | | * *either* the PIRQ handling or the I/OAPIC depending on whether |
471 | | * the former wants it. |
472 | | * |
473 | | * Additionally, this hook allows the Xen event channel GSI to |
474 | | * work around QEMU's lack of support for shared level interrupts, |
475 | | * by keeping track of the externally driven state of the pin and |
476 | | * implementing a logical OR with the state of the evtchn GSI. |
477 | | */ |
478 | 31.5M | if (xen_mode == XEN_EMULATE) { |
479 | 0 | bypass_ioapic = xen_evtchn_set_gsi(n, &level); |
480 | 0 | } |
481 | 31.5M | #endif |
482 | | |
483 | 31.5M | switch (n) { |
484 | 29.0M | case 0 ... ISA_NUM_IRQS - 1: |
485 | 29.0M | if (s->i8259_irq[n]) { |
486 | | /* Under KVM, Kernel will forward to both PIC and IOAPIC */ |
487 | 29.0M | qemu_set_irq(s->i8259_irq[n], level); |
488 | 29.0M | } |
489 | | /* fall through */ |
490 | 31.5M | case ISA_NUM_IRQS ... IOAPIC_NUM_PINS - 1: |
491 | 31.5M | if (!bypass_ioapic) { |
492 | 31.5M | qemu_set_irq(s->ioapic_irq[n], level); |
493 | 31.5M | } |
494 | 31.5M | break; |
495 | 0 | case IO_APIC_SECONDARY_IRQBASE |
496 | 0 | ... IO_APIC_SECONDARY_IRQBASE + IOAPIC_NUM_PINS - 1: |
497 | 0 | qemu_set_irq(s->ioapic2_irq[n - IO_APIC_SECONDARY_IRQBASE], level); |
498 | 0 | break; |
499 | 31.5M | } |
500 | 31.5M | } |
501 | | |
502 | | void ioapic_init_gsi(GSIState *gsi_state, Object *parent) |
503 | 63 | { |
504 | 63 | DeviceState *dev; |
505 | 63 | SysBusDevice *d; |
506 | 63 | unsigned int i; |
507 | | |
508 | 63 | assert(parent); |
509 | 63 | if (kvm_ioapic_in_kernel()) { |
510 | 0 | dev = qdev_new(TYPE_KVM_IOAPIC); |
511 | 63 | } else { |
512 | 63 | dev = qdev_new(TYPE_IOAPIC); |
513 | 63 | } |
514 | 63 | object_property_add_child(parent, "ioapic", OBJECT(dev)); |
515 | 63 | d = SYS_BUS_DEVICE(dev); |
516 | 63 | sysbus_realize_and_unref(d, &error_fatal); |
517 | 63 | sysbus_mmio_map(d, 0, IO_APIC_DEFAULT_ADDRESS); |
518 | | |
519 | 1.57k | for (i = 0; i < IOAPIC_NUM_PINS; i++) { |
520 | 1.51k | gsi_state->ioapic_irq[i] = qdev_get_gpio_in(dev, i); |
521 | 1.51k | } |
522 | 63 | } |
523 | | |
524 | | DeviceState *ioapic_init_secondary(GSIState *gsi_state) |
525 | 0 | { |
526 | 0 | DeviceState *dev; |
527 | 0 | SysBusDevice *d; |
528 | 0 | unsigned int i; |
529 | |
|
530 | 0 | dev = qdev_new(TYPE_IOAPIC); |
531 | 0 | d = SYS_BUS_DEVICE(dev); |
532 | 0 | sysbus_realize_and_unref(d, &error_fatal); |
533 | 0 | sysbus_mmio_map(d, 0, IO_APIC_SECONDARY_ADDRESS); |
534 | |
|
535 | 0 | for (i = 0; i < IOAPIC_NUM_PINS; i++) { |
536 | 0 | gsi_state->ioapic2_irq[i] = qdev_get_gpio_in(dev, i); |
537 | 0 | } |
538 | 0 | return dev; |
539 | 0 | } |
540 | | |
541 | | /* |
542 | | * The entry point into the kernel for PVH boot is different from |
543 | | * the native entry point. The PVH entry is defined by the x86/HVM |
544 | | * direct boot ABI and is available in an ELFNOTE in the kernel binary. |
545 | | * |
546 | | * This function is passed to load_elf() when it is called from |
547 | | * load_elfboot() which then additionally checks for an ELF Note of |
548 | | * type XEN_ELFNOTE_PHYS32_ENTRY and passes it to this function to |
549 | | * parse the PVH entry address from the ELF Note. |
550 | | * |
551 | | * Due to trickery in elf_opts.h, load_elf() is actually available as |
552 | | * load_elf32() or load_elf64() and this routine needs to be able |
553 | | * to deal with being called as 32 or 64 bit. |
554 | | * |
555 | | * The address of the PVH entry point is saved to the 'pvh_start_addr' |
556 | | * global variable. (although the entry point is 32-bit, the kernel |
557 | | * binary can be either 32-bit or 64-bit). |
558 | | */ |
559 | | static uint64_t read_pvh_start_addr(void *arg1, void *arg2, bool is64) |
560 | 0 | { |
561 | 0 | size_t *elf_note_data_addr; |
562 | | |
563 | | /* Check if ELF Note header passed in is valid */ |
564 | 0 | if (arg1 == NULL) { |
565 | 0 | return 0; |
566 | 0 | } |
567 | | |
568 | 0 | if (is64) { |
569 | 0 | struct elf64_note *nhdr64 = (struct elf64_note *)arg1; |
570 | 0 | uint64_t nhdr_size64 = sizeof(struct elf64_note); |
571 | 0 | uint64_t phdr_align = *(uint64_t *)arg2; |
572 | 0 | uint64_t nhdr_namesz = nhdr64->n_namesz; |
573 | |
|
574 | 0 | elf_note_data_addr = |
575 | 0 | ((void *)nhdr64) + nhdr_size64 + |
576 | 0 | QEMU_ALIGN_UP(nhdr_namesz, phdr_align); |
577 | |
|
578 | 0 | pvh_start_addr = tswap64(*elf_note_data_addr); |
579 | 0 | } else { |
580 | 0 | struct elf32_note *nhdr32 = (struct elf32_note *)arg1; |
581 | 0 | uint32_t nhdr_size32 = sizeof(struct elf32_note); |
582 | 0 | uint32_t phdr_align = *(uint32_t *)arg2; |
583 | 0 | uint32_t nhdr_namesz = nhdr32->n_namesz; |
584 | |
|
585 | 0 | elf_note_data_addr = |
586 | 0 | ((void *)nhdr32) + nhdr_size32 + |
587 | 0 | QEMU_ALIGN_UP(nhdr_namesz, phdr_align); |
588 | |
|
589 | 0 | pvh_start_addr = tswap32(*(uint32_t *)elf_note_data_addr); |
590 | 0 | } |
591 | |
|
592 | 0 | return pvh_start_addr; |
593 | 0 | } |
594 | | |
595 | | static bool load_elfboot(const char *kernel_filename, |
596 | | int kernel_file_size, |
597 | | uint8_t *header, |
598 | | size_t pvh_xen_start_addr, |
599 | | FWCfgState *fw_cfg) |
600 | 0 | { |
601 | 0 | uint32_t flags = 0; |
602 | 0 | uint32_t mh_load_addr = 0; |
603 | 0 | uint32_t elf_kernel_size = 0; |
604 | 0 | uint64_t elf_entry; |
605 | 0 | uint64_t elf_low, elf_high; |
606 | 0 | int kernel_size; |
607 | |
|
608 | 0 | if (ldl_le_p(header) != 0x464c457f) { |
609 | 0 | return false; /* no elfboot */ |
610 | 0 | } |
611 | | |
612 | 0 | bool elf_is64 = header[EI_CLASS] == ELFCLASS64; |
613 | 0 | flags = elf_is64 ? |
614 | 0 | ((Elf64_Ehdr *)header)->e_flags : ((Elf32_Ehdr *)header)->e_flags; |
615 | |
|
616 | 0 | if (flags & 0x00010004) { /* LOAD_ELF_HEADER_HAS_ADDR */ |
617 | 0 | error_report("elfboot unsupported flags = %x", flags); |
618 | 0 | exit(1); |
619 | 0 | } |
620 | | |
621 | 0 | uint64_t elf_note_type = XEN_ELFNOTE_PHYS32_ENTRY; |
622 | 0 | kernel_size = load_elf(kernel_filename, read_pvh_start_addr, |
623 | 0 | NULL, &elf_note_type, &elf_entry, |
624 | 0 | &elf_low, &elf_high, NULL, |
625 | 0 | ELFDATA2LSB, I386_ELF_MACHINE, 0, 0); |
626 | |
|
627 | 0 | if (kernel_size < 0) { |
628 | 0 | error_report("Error while loading elf kernel"); |
629 | 0 | exit(1); |
630 | 0 | } |
631 | 0 | mh_load_addr = elf_low; |
632 | 0 | elf_kernel_size = elf_high - elf_low; |
633 | |
|
634 | 0 | if (pvh_start_addr == 0) { |
635 | 0 | error_report("Error loading uncompressed kernel without PVH ELF Note"); |
636 | 0 | exit(1); |
637 | 0 | } |
638 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ENTRY, pvh_start_addr); |
639 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, mh_load_addr); |
640 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, elf_kernel_size); |
641 | |
|
642 | 0 | return true; |
643 | 0 | } |
644 | | |
645 | | void x86_load_linux(X86MachineState *x86ms, |
646 | | FWCfgState *fw_cfg, |
647 | | int acpi_data_size) |
648 | 0 | { |
649 | 0 | uint16_t protocol; |
650 | 0 | int setup_size, kernel_size, cmdline_size; |
651 | 0 | int dtb_size, setup_data_offset; |
652 | 0 | uint32_t initrd_max; |
653 | 0 | uint8_t header[8192], *setup, *kernel; |
654 | 0 | hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0; |
655 | 0 | FILE *f; |
656 | 0 | const char *vmode; |
657 | 0 | MachineState *machine = MACHINE(x86ms); |
658 | 0 | struct setup_data *setup_data; |
659 | 0 | const char *kernel_filename = machine->kernel_filename; |
660 | 0 | const char *initrd_filename = machine->initrd_filename; |
661 | 0 | const char *dtb_filename = machine->dtb; |
662 | 0 | const char *kernel_cmdline = machine->kernel_cmdline; |
663 | 0 | SevKernelLoaderContext sev_load_ctx = {}; |
664 | | |
665 | | /* Align to 16 bytes as a paranoia measure */ |
666 | 0 | cmdline_size = (strlen(kernel_cmdline) + 16) & ~15; |
667 | | |
668 | | /* load the kernel header */ |
669 | 0 | f = fopen(kernel_filename, "rb"); |
670 | 0 | if (!f) { |
671 | 0 | fprintf(stderr, "qemu: could not open kernel file '%s': %s\n", |
672 | 0 | kernel_filename, strerror(errno)); |
673 | 0 | exit(1); |
674 | 0 | } |
675 | | |
676 | 0 | kernel_size = get_file_size(f); |
677 | 0 | if (!kernel_size || |
678 | 0 | fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) != |
679 | 0 | MIN(ARRAY_SIZE(header), kernel_size)) { |
680 | 0 | fprintf(stderr, "qemu: could not load kernel '%s': %s\n", |
681 | 0 | kernel_filename, strerror(errno)); |
682 | 0 | exit(1); |
683 | 0 | } |
684 | | |
685 | | /* |
686 | | * kernel protocol version. |
687 | | * Please see https://www.kernel.org/doc/Documentation/x86/boot.txt |
688 | | */ |
689 | 0 | if (ldl_le_p(header + 0x202) == 0x53726448) /* Magic signature "HdrS" */ { |
690 | 0 | protocol = lduw_le_p(header + 0x206); |
691 | 0 | } else { |
692 | | /* |
693 | | * This could be a multiboot kernel. If it is, let's stop treating it |
694 | | * like a Linux kernel. |
695 | | * Note: some multiboot images could be in the ELF format (the same of |
696 | | * PVH), so we try multiboot first since we check the multiboot magic |
697 | | * header before to load it. |
698 | | */ |
699 | 0 | if (load_multiboot(x86ms, fw_cfg, f, kernel_filename, initrd_filename, |
700 | 0 | kernel_cmdline, kernel_size, header)) { |
701 | 0 | return; |
702 | 0 | } |
703 | | /* |
704 | | * Check if the file is an uncompressed kernel file (ELF) and load it, |
705 | | * saving the PVH entry point used by the x86/HVM direct boot ABI. |
706 | | * If load_elfboot() is successful, populate the fw_cfg info. |
707 | | */ |
708 | 0 | if (load_elfboot(kernel_filename, kernel_size, |
709 | 0 | header, pvh_start_addr, fw_cfg)) { |
710 | 0 | fclose(f); |
711 | |
|
712 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, |
713 | 0 | strlen(kernel_cmdline) + 1); |
714 | 0 | fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); |
715 | |
|
716 | 0 | setup = g_memdup2(header, sizeof(header)); |
717 | |
|
718 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, sizeof(header)); |
719 | 0 | fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, |
720 | 0 | setup, sizeof(header)); |
721 | | |
722 | | /* load initrd */ |
723 | 0 | if (initrd_filename) { |
724 | 0 | GMappedFile *mapped_file; |
725 | 0 | gsize initrd_size; |
726 | 0 | gchar *initrd_data; |
727 | 0 | GError *gerr = NULL; |
728 | |
|
729 | 0 | mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); |
730 | 0 | if (!mapped_file) { |
731 | 0 | fprintf(stderr, "qemu: error reading initrd %s: %s\n", |
732 | 0 | initrd_filename, gerr->message); |
733 | 0 | exit(1); |
734 | 0 | } |
735 | 0 | x86ms->initrd_mapped_file = mapped_file; |
736 | |
|
737 | 0 | initrd_data = g_mapped_file_get_contents(mapped_file); |
738 | 0 | initrd_size = g_mapped_file_get_length(mapped_file); |
739 | 0 | initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; |
740 | 0 | if (initrd_size >= initrd_max) { |
741 | 0 | fprintf(stderr, "qemu: initrd is too large, cannot support." |
742 | 0 | "(max: %"PRIu32", need %"PRId64")\n", |
743 | 0 | initrd_max, (uint64_t)initrd_size); |
744 | 0 | exit(1); |
745 | 0 | } |
746 | | |
747 | 0 | initrd_addr = (initrd_max - initrd_size) & ~4095; |
748 | |
|
749 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); |
750 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); |
751 | 0 | fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, |
752 | 0 | initrd_size); |
753 | 0 | } |
754 | | |
755 | 0 | option_rom[nb_option_roms].bootindex = 0; |
756 | 0 | option_rom[nb_option_roms].name = "pvh.bin"; |
757 | 0 | nb_option_roms++; |
758 | |
|
759 | 0 | return; |
760 | 0 | } |
761 | 0 | protocol = 0; |
762 | 0 | } |
763 | | |
764 | 0 | if (protocol < 0x200 || !(header[0x211] & 0x01)) { |
765 | | /* Low kernel */ |
766 | 0 | real_addr = 0x90000; |
767 | 0 | cmdline_addr = 0x9a000 - cmdline_size; |
768 | 0 | prot_addr = 0x10000; |
769 | 0 | } else if (protocol < 0x202) { |
770 | | /* High but ancient kernel */ |
771 | 0 | real_addr = 0x90000; |
772 | 0 | cmdline_addr = 0x9a000 - cmdline_size; |
773 | 0 | prot_addr = 0x100000; |
774 | 0 | } else { |
775 | | /* High and recent kernel */ |
776 | 0 | real_addr = 0x10000; |
777 | 0 | cmdline_addr = 0x20000; |
778 | 0 | prot_addr = 0x100000; |
779 | 0 | } |
780 | | |
781 | | /* highest address for loading the initrd */ |
782 | 0 | if (protocol >= 0x20c && |
783 | 0 | lduw_le_p(header + 0x236) & XLF_CAN_BE_LOADED_ABOVE_4G) { |
784 | | /* |
785 | | * Linux has supported initrd up to 4 GB for a very long time (2007, |
786 | | * long before XLF_CAN_BE_LOADED_ABOVE_4G which was added in 2013), |
787 | | * though it only sets initrd_max to 2 GB to "work around bootloader |
788 | | * bugs". Luckily, QEMU firmware(which does something like bootloader) |
789 | | * has supported this. |
790 | | * |
791 | | * It's believed that if XLF_CAN_BE_LOADED_ABOVE_4G is set, initrd can |
792 | | * be loaded into any address. |
793 | | * |
794 | | * In addition, initrd_max is uint32_t simply because QEMU doesn't |
795 | | * support the 64-bit boot protocol (specifically the ext_ramdisk_image |
796 | | * field). |
797 | | * |
798 | | * Therefore here just limit initrd_max to UINT32_MAX simply as well. |
799 | | */ |
800 | 0 | initrd_max = UINT32_MAX; |
801 | 0 | } else if (protocol >= 0x203) { |
802 | 0 | initrd_max = ldl_le_p(header + 0x22c); |
803 | 0 | } else { |
804 | 0 | initrd_max = 0x37ffffff; |
805 | 0 | } |
806 | |
|
807 | 0 | if (initrd_max >= x86ms->below_4g_mem_size - acpi_data_size) { |
808 | 0 | initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; |
809 | 0 | } |
810 | |
|
811 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr); |
812 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline) + 1); |
813 | 0 | fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); |
814 | 0 | sev_load_ctx.cmdline_data = (char *)kernel_cmdline; |
815 | 0 | sev_load_ctx.cmdline_size = strlen(kernel_cmdline) + 1; |
816 | |
|
817 | 0 | if (protocol >= 0x202) { |
818 | 0 | stl_le_p(header + 0x228, cmdline_addr); |
819 | 0 | } else { |
820 | 0 | stw_le_p(header + 0x20, 0xA33F); |
821 | 0 | stw_le_p(header + 0x22, cmdline_addr - real_addr); |
822 | 0 | } |
823 | | |
824 | | /* handle vga= parameter */ |
825 | 0 | vmode = strstr(kernel_cmdline, "vga="); |
826 | 0 | if (vmode) { |
827 | 0 | unsigned int video_mode; |
828 | 0 | const char *end; |
829 | 0 | int ret; |
830 | | /* skip "vga=" */ |
831 | 0 | vmode += 4; |
832 | 0 | if (!strncmp(vmode, "normal", 6)) { |
833 | 0 | video_mode = 0xffff; |
834 | 0 | } else if (!strncmp(vmode, "ext", 3)) { |
835 | 0 | video_mode = 0xfffe; |
836 | 0 | } else if (!strncmp(vmode, "ask", 3)) { |
837 | 0 | video_mode = 0xfffd; |
838 | 0 | } else { |
839 | 0 | ret = qemu_strtoui(vmode, &end, 0, &video_mode); |
840 | 0 | if (ret != 0 || (*end && *end != ' ')) { |
841 | 0 | fprintf(stderr, "qemu: invalid 'vga=' kernel parameter.\n"); |
842 | 0 | exit(1); |
843 | 0 | } |
844 | 0 | } |
845 | 0 | stw_le_p(header + 0x1fa, video_mode); |
846 | 0 | } |
847 | | |
848 | | /* loader type */ |
849 | | /* |
850 | | * High nybble = B reserved for QEMU; low nybble is revision number. |
851 | | * If this code is substantially changed, you may want to consider |
852 | | * incrementing the revision. |
853 | | */ |
854 | 0 | if (protocol >= 0x200) { |
855 | 0 | header[0x210] = 0xB0; |
856 | 0 | } |
857 | | /* heap */ |
858 | 0 | if (protocol >= 0x201) { |
859 | 0 | header[0x211] |= 0x80; /* CAN_USE_HEAP */ |
860 | 0 | stw_le_p(header + 0x224, cmdline_addr - real_addr - 0x200); |
861 | 0 | } |
862 | | |
863 | | /* load initrd */ |
864 | 0 | if (initrd_filename) { |
865 | 0 | GMappedFile *mapped_file; |
866 | 0 | gsize initrd_size; |
867 | 0 | gchar *initrd_data; |
868 | 0 | GError *gerr = NULL; |
869 | |
|
870 | 0 | if (protocol < 0x200) { |
871 | 0 | fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n"); |
872 | 0 | exit(1); |
873 | 0 | } |
874 | | |
875 | 0 | mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); |
876 | 0 | if (!mapped_file) { |
877 | 0 | fprintf(stderr, "qemu: error reading initrd %s: %s\n", |
878 | 0 | initrd_filename, gerr->message); |
879 | 0 | exit(1); |
880 | 0 | } |
881 | 0 | x86ms->initrd_mapped_file = mapped_file; |
882 | |
|
883 | 0 | initrd_data = g_mapped_file_get_contents(mapped_file); |
884 | 0 | initrd_size = g_mapped_file_get_length(mapped_file); |
885 | 0 | if (initrd_size >= initrd_max) { |
886 | 0 | fprintf(stderr, "qemu: initrd is too large, cannot support." |
887 | 0 | "(max: %"PRIu32", need %"PRId64")\n", |
888 | 0 | initrd_max, (uint64_t)initrd_size); |
889 | 0 | exit(1); |
890 | 0 | } |
891 | | |
892 | 0 | initrd_addr = (initrd_max - initrd_size) & ~4095; |
893 | |
|
894 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); |
895 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); |
896 | 0 | fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size); |
897 | 0 | sev_load_ctx.initrd_data = initrd_data; |
898 | 0 | sev_load_ctx.initrd_size = initrd_size; |
899 | |
|
900 | 0 | stl_le_p(header + 0x218, initrd_addr); |
901 | 0 | stl_le_p(header + 0x21c, initrd_size); |
902 | 0 | } |
903 | | |
904 | | /* load kernel and setup */ |
905 | 0 | setup_size = header[0x1f1]; |
906 | 0 | if (setup_size == 0) { |
907 | 0 | setup_size = 4; |
908 | 0 | } |
909 | 0 | setup_size = (setup_size + 1) * 512; |
910 | 0 | if (setup_size > kernel_size) { |
911 | 0 | fprintf(stderr, "qemu: invalid kernel header\n"); |
912 | 0 | exit(1); |
913 | 0 | } |
914 | | |
915 | 0 | setup = g_malloc(setup_size); |
916 | 0 | kernel = g_malloc(kernel_size); |
917 | 0 | fseek(f, 0, SEEK_SET); |
918 | 0 | if (fread(setup, 1, setup_size, f) != setup_size) { |
919 | 0 | fprintf(stderr, "fread() failed\n"); |
920 | 0 | exit(1); |
921 | 0 | } |
922 | 0 | fseek(f, 0, SEEK_SET); |
923 | 0 | if (fread(kernel, 1, kernel_size, f) != kernel_size) { |
924 | 0 | fprintf(stderr, "fread() failed\n"); |
925 | 0 | exit(1); |
926 | 0 | } |
927 | 0 | fclose(f); |
928 | | |
929 | | /* append dtb to kernel */ |
930 | 0 | if (dtb_filename) { |
931 | 0 | if (protocol < 0x209) { |
932 | 0 | fprintf(stderr, "qemu: Linux kernel too old to load a dtb\n"); |
933 | 0 | exit(1); |
934 | 0 | } |
935 | | |
936 | 0 | dtb_size = get_image_size(dtb_filename, NULL); |
937 | 0 | if (dtb_size <= 0) { |
938 | 0 | fprintf(stderr, "qemu: error reading dtb %s: %s\n", |
939 | 0 | dtb_filename, strerror(errno)); |
940 | 0 | exit(1); |
941 | 0 | } |
942 | | |
943 | 0 | setup_data_offset = QEMU_ALIGN_UP(kernel_size, 16); |
944 | 0 | kernel_size = setup_data_offset + sizeof(struct setup_data) + dtb_size; |
945 | 0 | kernel = g_realloc(kernel, kernel_size); |
946 | |
|
947 | 0 | stq_le_p(header + 0x250, prot_addr + setup_data_offset); |
948 | |
|
949 | 0 | setup_data = (struct setup_data *)(kernel + setup_data_offset); |
950 | 0 | setup_data->next = 0; |
951 | 0 | setup_data->type = cpu_to_le32(SETUP_DTB); |
952 | 0 | setup_data->len = cpu_to_le32(dtb_size); |
953 | |
|
954 | 0 | load_image_size(dtb_filename, setup_data->data, dtb_size); |
955 | 0 | } |
956 | | |
957 | | /* |
958 | | * If we're starting an encrypted VM, it will be OVMF based, which uses the |
959 | | * efi stub for booting and doesn't require any values to be placed in the |
960 | | * kernel header. We therefore don't update the header so the hash of the |
961 | | * kernel on the other side of the fw_cfg interface matches the hash of the |
962 | | * file the user passed in. |
963 | | */ |
964 | 0 | if (!MACHINE(x86ms)->cgs && protocol > 0) { |
965 | 0 | memcpy(setup, header, MIN(sizeof(header), setup_size)); |
966 | 0 | } |
967 | |
|
968 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr); |
969 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size - setup_size); |
970 | 0 | fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, |
971 | 0 | kernel + setup_size, kernel_size - setup_size); |
972 | 0 | sev_load_ctx.kernel_data = (char *)kernel + setup_size; |
973 | 0 | sev_load_ctx.kernel_size = kernel_size - setup_size; |
974 | |
|
975 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr); |
976 | 0 | fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size); |
977 | 0 | fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size); |
978 | 0 | sev_load_ctx.setup_data = (char *)setup; |
979 | 0 | sev_load_ctx.setup_size = setup_size; |
980 | | |
981 | | /* kernel without setup header patches */ |
982 | 0 | fw_cfg_add_file(fw_cfg, "etc/boot/kernel", kernel, kernel_size); |
983 | |
|
984 | 0 | if (machine->shim_filename) { |
985 | 0 | load_image_to_fw_cfg_file(fw_cfg, "etc/boot/shim", |
986 | 0 | machine->shim_filename); |
987 | 0 | } |
988 | |
|
989 | 0 | if (sev_enabled()) { |
990 | 0 | sev_add_kernel_loader_hashes(&sev_load_ctx, &error_fatal); |
991 | 0 | } |
992 | |
|
993 | 0 | option_rom[nb_option_roms].bootindex = 0; |
994 | 0 | assert(fw_cfg_dma_enabled(fw_cfg)); |
995 | 0 | option_rom[nb_option_roms].name = "linuxboot_dma.bin"; |
996 | 0 | nb_option_roms++; |
997 | 0 | } |