kvm.h 16.1 KB
Newer Older
A
aliguori 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * QEMU KVM support
 *
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#ifndef QEMU_KVM_H
#define QEMU_KVM_H

17
#include <errno.h>
18
#include "config-host.h"
19
#include "qemu/queue.h"
20
#include "qom/cpu.h"
21
#include "exec/memattrs.h"
22
#include "hw/irq.h"
A
aliguori 已提交
23

24 25
#ifdef CONFIG_KVM
#include <linux/kvm.h>
26
#include <linux/kvm_para.h>
27 28 29 30 31 32 33 34 35 36 37 38 39 40
#else
/* These constants must never be used at runtime if kvm_enabled() is false.
 * They exist so we don't need #ifdefs around KVM-specific code that already
 * checks kvm_enabled() properly.
 */
#define KVM_CPUID_SIGNATURE      0
#define KVM_CPUID_FEATURES       0
#define KVM_FEATURE_CLOCKSOURCE  0
#define KVM_FEATURE_NOP_IO_DELAY 0
#define KVM_FEATURE_MMU_OP       0
#define KVM_FEATURE_CLOCKSOURCE2 0
#define KVM_FEATURE_ASYNC_PF     0
#define KVM_FEATURE_STEAL_TIME   0
#define KVM_FEATURE_PV_EOI       0
41
#define KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 0
42
#endif
A
aliguori 已提交
43

44
extern bool kvm_allowed;
45
extern bool kvm_kernel_irqchip;
46
extern bool kvm_async_interrupts_allowed;
47
extern bool kvm_halt_in_kernel_allowed;
48
extern bool kvm_eventfds_allowed;
49
extern bool kvm_irqfds_allowed;
50
extern bool kvm_resamplefds_allowed;
51
extern bool kvm_msi_via_irqfd_allowed;
52
extern bool kvm_gsi_routing_allowed;
53
extern bool kvm_gsi_direct_mapping;
54
extern bool kvm_readonly_mem_allowed;
55 56

#if defined CONFIG_KVM || !defined NEED_CPU_H
57
#define kvm_enabled()           (kvm_allowed)
58 59 60 61 62 63 64 65 66 67 68
/**
 * kvm_irqchip_in_kernel:
 *
 * Returns: true if the user asked us to create an in-kernel
 * irqchip via the "kernel_irqchip=on" machine option.
 * What this actually means is architecture and machine model
 * specific: on PC, for instance, it means that the LAPIC,
 * IOAPIC and PIT are all in kernel. This function should never
 * be used from generic target-independent code: use one of the
 * following functions or some other specific check instead.
 */
69
#define kvm_irqchip_in_kernel() (kvm_kernel_irqchip)
70 71 72 73 74 75 76 77 78 79 80

/**
 * kvm_async_interrupts_enabled:
 *
 * Returns: true if we can deliver interrupts to KVM
 * asynchronously (ie by ioctl from any thread at any time)
 * rather than having to do interrupt delivery synchronously
 * (where the vcpu must be stopped at a suitable point first).
 */
#define kvm_async_interrupts_enabled() (kvm_async_interrupts_allowed)

81 82 83 84 85 86 87 88
/**
 * kvm_halt_in_kernel
 *
 * Returns: true if halted cpus should still get a KVM_RUN ioctl to run
 * inside of kernel space. This only works if MP state is implemented.
 */
#define kvm_halt_in_kernel() (kvm_halt_in_kernel_allowed)

89 90 91 92 93 94 95 96 97
/**
 * kvm_eventfds_enabled:
 *
 * Returns: true if we can use eventfds to receive notifications
 * from a KVM CPU (ie the kernel supports eventds and we are running
 * with a configuration where it is meaningful to use them).
 */
#define kvm_eventfds_enabled() (kvm_eventfds_allowed)

98 99 100 101 102 103 104 105 106
/**
 * kvm_irqfds_enabled:
 *
 * Returns: true if we can use irqfds to inject interrupts into
 * a KVM CPU (ie the kernel supports irqfds and we are running
 * with a configuration where it is meaningful to use them).
 */
#define kvm_irqfds_enabled() (kvm_irqfds_allowed)

107 108 109 110 111 112 113 114 115
/**
 * kvm_resamplefds_enabled:
 *
 * Returns: true if we can use resamplefds to inject interrupts into
 * a KVM CPU (ie the kernel supports resamplefds and we are running
 * with a configuration where it is meaningful to use them).
 */
#define kvm_resamplefds_enabled() (kvm_resamplefds_allowed)

116 117 118 119 120 121 122 123 124
/**
 * kvm_msi_via_irqfd_enabled:
 *
 * Returns: true if we can route a PCI MSI (Message Signaled Interrupt)
 * to a KVM CPU via an irqfd. This requires that the kernel supports
 * this and that we're running in a configuration that permits it.
 */
#define kvm_msi_via_irqfd_enabled() (kvm_msi_via_irqfd_allowed)

125 126 127 128 129 130 131 132
/**
 * kvm_gsi_routing_enabled:
 *
 * Returns: true if GSI routing is enabled (ie the kernel supports
 * it and we're running in a configuration that permits it).
 */
#define kvm_gsi_routing_enabled() (kvm_gsi_routing_allowed)

133 134 135 136 137 138 139
/**
 * kvm_gsi_direct_mapping:
 *
 * Returns: true if GSI direct mapping is enabled.
 */
#define kvm_gsi_direct_mapping() (kvm_gsi_direct_mapping)

140 141 142 143 144 145 146 147
/**
 * kvm_readonly_mem_enabled:
 *
 * Returns: true if KVM readonly memory is enabled (ie the kernel
 * supports it and we're running in a configuration that permits it).
 */
#define kvm_readonly_mem_enabled() (kvm_readonly_mem_allowed)

A
aliguori 已提交
148
#else
149 150
#define kvm_enabled()           (0)
#define kvm_irqchip_in_kernel() (false)
151
#define kvm_async_interrupts_enabled() (false)
152
#define kvm_halt_in_kernel() (false)
153
#define kvm_eventfds_enabled() (false)
154
#define kvm_irqfds_enabled() (false)
155
#define kvm_resamplefds_enabled() (false)
156
#define kvm_msi_via_irqfd_enabled() (false)
157
#define kvm_gsi_routing_allowed() (false)
158
#define kvm_gsi_direct_mapping() (false)
159
#define kvm_readonly_mem_enabled() (false)
A
aliguori 已提交
160 161 162
#endif

struct kvm_run;
163
struct kvm_lapic_state;
164
struct kvm_irq_routing_entry;
A
aliguori 已提交
165

166 167 168 169 170 171 172 173
typedef struct KVMCapabilityInfo {
    const char *name;
    int value;
} KVMCapabilityInfo;

#define KVM_CAP_INFO(CAP) { "KVM_CAP_" stringify(CAP), KVM_CAP_##CAP }
#define KVM_CAP_LAST_INFO { NULL, 0 }

174 175 176 177
struct KVMState;
typedef struct KVMState KVMState;
extern KVMState *kvm_state;

A
aliguori 已提交
178 179
/* external API */

180
bool kvm_has_free_slot(MachineState *ms);
181 182 183
int kvm_has_sync_mmu(void);
int kvm_has_vcpu_events(void);
int kvm_has_robust_singlestep(void);
184
int kvm_has_debugregs(void);
185 186
int kvm_has_xsave(void);
int kvm_has_xcrs(void);
J
Jan Kiszka 已提交
187
int kvm_has_pit_state2(void);
188
int kvm_has_many_ioeventfds(void);
189
int kvm_has_gsi_routing(void);
190
int kvm_has_intx_set_mask(void);
191

192
int kvm_init_vcpu(CPUState *cpu);
193
int kvm_cpu_exec(CPUState *cpu);
A
aliguori 已提交
194

195
#ifdef NEED_CPU_H
A
aliguori 已提交
196

197
void kvm_setup_guest_memory(void *start, size_t size);
198
void kvm_flush_coalesced_mmio_buffer(void);
A
aliguori 已提交
199

200
int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
201
                          target_ulong len, int type);
202
int kvm_remove_breakpoint(CPUState *cpu, target_ulong addr,
203
                          target_ulong len, int type);
204
void kvm_remove_all_breakpoints(CPUState *cpu);
205
int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap);
B
Blue Swirl 已提交
206
#ifndef _WIN32
207
int kvm_set_signal_mask(CPUState *cpu, const sigset_t *sigset);
B
Blue Swirl 已提交
208
#endif
209

210
int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
211 212
int kvm_on_sigbus(int code, void *addr);

A
aliguori 已提交
213 214
/* internal API */

215
int kvm_ioctl(KVMState *s, int type, ...);
A
aliguori 已提交
216

217
int kvm_vm_ioctl(KVMState *s, int type, ...);
A
aliguori 已提交
218

219
int kvm_vcpu_ioctl(CPUState *cpu, int type, ...);
A
aliguori 已提交
220

221 222 223 224 225 226 227 228 229
/**
 * kvm_device_ioctl - call an ioctl on a kvm device
 * @fd: The KVM device file descriptor as returned from KVM_CREATE_DEVICE
 * @type: The device-ctrl ioctl number
 *
 * Returns: -errno on error, nonnegative on success
 */
int kvm_device_ioctl(int fd, int type, ...);

230 231 232 233 234 235 236 237 238 239 240 241
/**
 * kvm_vm_check_attr - check for existence of a specific vm attribute
 * @s: The KVMState pointer
 * @group: the group
 * @attr: the attribute of that group to query for
 *
 * Returns: 1 if the attribute exists
 *          0 if the attribute either does not exist or if the vm device
 *            interface is unavailable
 */
int kvm_vm_check_attr(KVMState *s, uint32_t group, uint64_t attr);

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
/**
 * kvm_device_check_attr - check for existence of a specific device attribute
 * @fd: The device file descriptor
 * @group: the group
 * @attr: the attribute of that group to query for
 *
 * Returns: 1 if the attribute exists
 *          0 if the attribute either does not exist or if the vm device
 *            interface is unavailable
 */
int kvm_device_check_attr(int fd, uint32_t group, uint64_t attr);

/**
 * kvm_device_access - set or get value of a specific vm attribute
 * @fd: The device file descriptor
 * @group: the group
 * @attr: the attribute of that group to set or get
 * @val: pointer to a storage area for the value
 * @write: true for set and false for get operation
 *
 * This function is not allowed to fail. Use kvm_device_check_attr()
 * in order to check for the availability of optional attributes.
 */
void kvm_device_access(int fd, int group, uint64_t attr,
                       void *val, bool write);

268 269 270 271 272 273 274 275 276 277 278 279 280
/**
 * kvm_create_device - create a KVM device for the device control API
 * @KVMState: The KVMState pointer
 * @type: The KVM device type (see Documentation/virtual/kvm/devices in the
 *        kernel source)
 * @test: If true, only test if device can be created, but don't actually
 *        create the device.
 *
 * Returns: -errno on error, nonnegative on success: @test ? 0 : device fd;
 */
int kvm_create_device(KVMState *s, uint64_t type, bool test);


A
aliguori 已提交
281 282
/* Arch specific hooks */

283 284
extern const KVMCapabilityInfo kvm_arch_required_capabilities[];

A
Andreas Färber 已提交
285
void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run);
286
MemTxAttrs kvm_arch_post_run(CPUState *cpu, struct kvm_run *run);
A
aliguori 已提交
287

A
Andreas Färber 已提交
288
int kvm_arch_handle_exit(CPUState *cpu, struct kvm_run *run);
A
aliguori 已提交
289

A
Andreas Färber 已提交
290
int kvm_arch_process_async_events(CPUState *cpu);
M
Marcelo Tosatti 已提交
291

A
Andreas Färber 已提交
292
int kvm_arch_get_registers(CPUState *cpu);
A
aliguori 已提交
293

294 295 296 297 298 299 300
/* state subset only touched by the VCPU itself during runtime */
#define KVM_PUT_RUNTIME_STATE   1
/* state subset modified during VCPU reset */
#define KVM_PUT_RESET_STATE     2
/* full state set, modified during initialization or on vmload */
#define KVM_PUT_FULL_STATE      3

A
Andreas Färber 已提交
301
int kvm_arch_put_registers(CPUState *cpu, int level);
A
aliguori 已提交
302

303
int kvm_arch_init(MachineState *ms, KVMState *s);
A
aliguori 已提交
304

A
Andreas Färber 已提交
305
int kvm_arch_init_vcpu(CPUState *cpu);
A
aliguori 已提交
306

307 308 309
/* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */
unsigned long kvm_arch_vcpu_id(CPUState *cpu);

A
Andreas Färber 已提交
310
int kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
311
int kvm_arch_on_sigbus(int code, void *addr);
M
Marcelo Tosatti 已提交
312

313 314
void kvm_arch_init_irq_routing(KVMState *s);

315 316 317
int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route,
                             uint64_t address, uint32_t data);

318 319
int kvm_arch_msi_data_to_gsi(uint32_t data);

320
int kvm_set_irq(KVMState *s, int irq, int level);
321
int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg);
322

323
void kvm_irqchip_add_irq_route(KVMState *s, int gsi, int irqchip, int pin);
324
void kvm_irqchip_commit_routes(KVMState *s);
325

326 327 328
void kvm_put_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);
void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);

329 330 331 332 333 334 335
struct kvm_guest_debug;
struct kvm_debug_exit_arch;

struct kvm_sw_breakpoint {
    target_ulong pc;
    target_ulong saved_insn;
    int use_count;
B
Blue Swirl 已提交
336
    QTAILQ_ENTRY(kvm_sw_breakpoint) entry;
337 338
};

B
Blue Swirl 已提交
339
QTAILQ_HEAD(kvm_sw_breakpoint_head, kvm_sw_breakpoint);
340

341
struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *cpu,
342 343
                                                 target_ulong pc);

344
int kvm_sw_breakpoints_active(CPUState *cpu);
345

346
int kvm_arch_insert_sw_breakpoint(CPUState *cpu,
347
                                  struct kvm_sw_breakpoint *bp);
348
int kvm_arch_remove_sw_breakpoint(CPUState *cpu,
349 350 351 352 353 354 355
                                  struct kvm_sw_breakpoint *bp);
int kvm_arch_insert_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type);
int kvm_arch_remove_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type);
void kvm_arch_remove_all_hw_breakpoints(void);

A
Andreas Färber 已提交
356
void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg);
357

A
Andreas Färber 已提交
358
bool kvm_arch_stop_on_emulation_error(CPUState *cpu);
359

360 361
int kvm_check_extension(KVMState *s, unsigned int extension);

362 363
int kvm_vm_check_extension(KVMState *s, unsigned int extension);

364 365 366 367 368 369 370 371
#define kvm_vm_enable_cap(s, capability, cap_flags, ...)             \
    ({                                                               \
        struct kvm_enable_cap cap = {                                \
            .cap = capability,                                       \
            .flags = cap_flags,                                      \
        };                                                           \
        uint64_t args_tmp[] = { __VA_ARGS__ };                       \
        int i;                                                       \
372
        for (i = 0; i < (int)ARRAY_SIZE(args_tmp) &&                 \
373 374 375 376 377 378 379 380 381 382 383 384 385 386
                     i < ARRAY_SIZE(cap.args); i++) {                \
            cap.args[i] = args_tmp[i];                               \
        }                                                            \
        kvm_vm_ioctl(s, KVM_ENABLE_CAP, &cap);                       \
    })

#define kvm_vcpu_enable_cap(cpu, capability, cap_flags, ...)         \
    ({                                                               \
        struct kvm_enable_cap cap = {                                \
            .cap = capability,                                       \
            .flags = cap_flags,                                      \
        };                                                           \
        uint64_t args_tmp[] = { __VA_ARGS__ };                       \
        int i;                                                       \
387
        for (i = 0; i < (int)ARRAY_SIZE(args_tmp) &&                 \
388 389 390 391 392 393
                     i < ARRAY_SIZE(cap.args); i++) {                \
            cap.args[i] = args_tmp[i];                               \
        }                                                            \
        kvm_vcpu_ioctl(cpu, KVM_ENABLE_CAP, &cap);                   \
    })

394
uint32_t kvm_arch_get_supported_cpuid(KVMState *env, uint32_t function,
395
                                      uint32_t index, int reg);
396

397 398
void kvm_set_sigmask_len(KVMState *s, unsigned int sigmask_len);

399 400 401 402 403 404 405
#if !defined(CONFIG_USER_ONLY)
int kvm_physical_memory_addr_from_host(KVMState *s, void *ram_addr,
                                       hwaddr *phys_addr);
#endif

#endif /* NEED_CPU_H */

406
void kvm_cpu_synchronize_state(CPUState *cpu);
407 408
void kvm_cpu_synchronize_post_reset(CPUState *cpu);
void kvm_cpu_synchronize_post_init(CPUState *cpu);
M
Marcelo Tosatti 已提交
409
void kvm_cpu_clean_state(CPUState *cpu);
410

411 412 413 414 415 416 417 418 419
/* generic hooks - to be moved/refactored once there are more users */

static inline void cpu_synchronize_state(CPUState *cpu)
{
    if (kvm_enabled()) {
        kvm_cpu_synchronize_state(cpu);
    }
}

420
static inline void cpu_synchronize_post_reset(CPUState *cpu)
421 422
{
    if (kvm_enabled()) {
423
        kvm_cpu_synchronize_post_reset(cpu);
424 425 426
    }
}

427
static inline void cpu_synchronize_post_init(CPUState *cpu)
428 429
{
    if (kvm_enabled()) {
430
        kvm_cpu_synchronize_post_init(cpu);
431 432
    }
}
433

M
Marcelo Tosatti 已提交
434 435 436 437 438 439 440
static inline void cpu_clean_state(CPUState *cpu)
{
    if (kvm_enabled()) {
        kvm_cpu_clean_state(cpu);
    }
}

441
int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg);
442
int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg);
443
void kvm_irqchip_release_virq(KVMState *s, int virq);
444

445 446
int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter);

447 448 449 450
int kvm_irqchip_add_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
                                       EventNotifier *rn, int virq);
int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
                                          int virq);
451 452 453 454 455
int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
                                   EventNotifier *rn, qemu_irq irq);
int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n,
                                      qemu_irq irq);
void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi);
456 457
void kvm_pc_gsi_handler(void *opaque, int n, int level);
void kvm_pc_setup_irq_routing(bool pci_enabled);
458
void kvm_init_irq_routing(KVMState *s);
459 460 461 462 463 464 465 466 467 468 469 470

/**
 * kvm_arch_irqchip_create:
 * @KVMState: The KVMState pointer
 *
 * Allow architectures to create an in-kernel irq chip themselves.
 *
 * Returns: < 0: error
 *            0: irq chip was not created
 *          > 0: irq chip was created
 */
int kvm_arch_irqchip_create(KVMState *s);
471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490

/**
 * kvm_set_one_reg - set a register value in KVM via KVM_SET_ONE_REG ioctl
 * @id: The register ID
 * @source: The pointer to the value to be set. It must point to a variable
 *          of the correct type/size for the register being accessed.
 *
 * Returns: 0 on success, or a negative errno on failure.
 */
int kvm_set_one_reg(CPUState *cs, uint64_t id, void *source);

/**
 * kvm_get_one_reg - get a register value from KVM via KVM_GET_ONE_REG ioctl
 * @id: The register ID
 * @target: The pointer where the value is to be stored. It must point to a
 *          variable of the correct type/size for the register being accessed.
 *
 * Returns: 0 on success, or a negative errno on failure.
 */
int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target);
A
aliguori 已提交
491
#endif