int fd;
int vmfd;
int coalesced_mmio;
-#ifdef KVM_CAP_COALESCED_MMIO
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
-#endif
int broken_set_mem_region;
int migration_log;
int vcpu_events;
int many_ioeventfds;
};
-static KVMState *kvm_state;
+KVMState *kvm_state;
+
+static const KVMCapabilityInfo kvm_required_capabilites[] = {
+ KVM_CAP_INFO(USER_MEMORY),
+ KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
+ KVM_CAP_LAST_INFO
+};
static KVMSlot *kvm_alloc_slot(KVMState *s)
{
int i;
for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
- /* KVM private memory slots */
- if (i >= 8 && i < 12) {
- continue;
- }
if (s->slots[i].memory_size == 0) {
return &s->slots[i];
}
return kvm_state->pit_in_kernel;
}
-
int kvm_init_vcpu(CPUState *env)
{
KVMState *s = kvm_state;
env->kvm_fd = ret;
env->kvm_state = s;
+ env->kvm_vcpu_dirty = 1;
mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
+ ret = mmap_size;
DPRINTF("KVM_GET_VCPU_MMAP_SIZE failed\n");
goto err;
}
goto err;
}
-#ifdef KVM_CAP_COALESCED_MMIO
if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
s->coalesced_mmio_ring =
(void *)env->kvm_run + s->coalesced_mmio * PAGE_SIZE;
}
-#endif
ret = kvm_arch_init_vcpu(env);
if (ret == 0) {
/*
* dirty pages logging control
*/
-static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
- ram_addr_t size, int flags, int mask)
+
+static int kvm_mem_flags(KVMState *s, bool log_dirty)
+{
+ return log_dirty ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+}
+
+static int kvm_slot_dirty_pages_log_change(KVMSlot *mem, bool log_dirty)
{
KVMState *s = kvm_state;
- KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
+ int flags, mask = KVM_MEM_LOG_DIRTY_PAGES;
int old_flags;
- if (mem == NULL) {
- fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
- TARGET_FMT_plx "\n", __func__, phys_addr,
- (target_phys_addr_t)(phys_addr + size - 1));
- return -EINVAL;
- }
-
old_flags = mem->flags;
- flags = (mem->flags & ~mask) | flags;
+ flags = (mem->flags & ~mask) | kvm_mem_flags(s, log_dirty);
mem->flags = flags;
/* If nothing changed effectively, no need to issue ioctl */
if (s->migration_log) {
flags |= KVM_MEM_LOG_DIRTY_PAGES;
}
+
if (flags == old_flags) {
- return 0;
+ return 0;
}
return kvm_set_user_memory_region(s, mem);
}
-int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size)
+static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
+ ram_addr_t size, bool log_dirty)
+{
+ KVMState *s = kvm_state;
+ KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
+
+ if (mem == NULL) {
+ fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
+ TARGET_FMT_plx "\n", __func__, phys_addr,
+ (target_phys_addr_t)(phys_addr + size - 1));
+ return -EINVAL;
+ }
+ return kvm_slot_dirty_pages_log_change(mem, log_dirty);
+}
+
+static int kvm_log_start(CPUPhysMemoryClient *client,
+ target_phys_addr_t phys_addr, ram_addr_t size)
{
- return kvm_dirty_pages_log_change(phys_addr, size, KVM_MEM_LOG_DIRTY_PAGES,
- KVM_MEM_LOG_DIRTY_PAGES);
+ return kvm_dirty_pages_log_change(phys_addr, size, true);
}
-int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
+static int kvm_log_stop(CPUPhysMemoryClient *client,
+ target_phys_addr_t phys_addr, ram_addr_t size)
{
- return kvm_dirty_pages_log_change(phys_addr, size, 0,
- KVM_MEM_LOG_DIRTY_PAGES);
+ return kvm_dirty_pages_log_change(phys_addr, size, false);
}
static int kvm_set_migration_log(int enable)
break;
}
- size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS), HOST_LONG_BITS) / 8;
+ /* XXX bad kernel interface alert
+ * For dirty bitmap, kernel allocates array of size aligned to
+ * bits-per-long. But for case when the kernel is 64bits and
+ * the userspace is 32bits, userspace can't align to the same
+ * bits-per-long, since sizeof(long) is different between kernel
+ * and user space. This way, userspace will provide buffer which
+ * may be 4 bytes less than the kernel will use, resulting in
+ * userspace memory corruption (which is not detectable by valgrind
+ * too, in most cases).
+ * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
+ * a hope that sizeof(long) wont become >8 any time soon.
+ */
+ size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
+ /*HOST_LONG_BITS*/ 64) / 8;
if (!d.dirty_bitmap) {
d.dirty_bitmap = qemu_malloc(size);
} else if (size > allocated_size) {
int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio) {
ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
}
-#endif
return ret;
}
int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio) {
ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
}
-#endif
return ret;
}
static int kvm_check_many_ioeventfds(void)
{
- /* Older kernels have a 6 device limit on the KVM io bus. Find out so we
+ /* Userspace can use ioeventfd for io notification. This requires a host
+ * that supports eventfd(2) and an I/O thread; since eventfd does not
+ * support SIGIO it cannot interrupt the vcpu.
+ *
+ * Older kernels have a 6 device limit on the KVM io bus. Find out so we
* can avoid creating too many ioeventfds.
*/
-#ifdef CONFIG_EVENTFD
+#if defined(CONFIG_EVENTFD) && defined(CONFIG_IOTHREAD)
int ioeventfds[7];
int i, ret = 0;
for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) {
#endif
}
+static const KVMCapabilityInfo *
+kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
+{
+ while (list->name) {
+ if (!kvm_check_extension(s, list->value)) {
+ return list;
+ }
+ list++;
+ }
+ return NULL;
+}
+
static void kvm_set_phys_mem(target_phys_addr_t start_addr, ram_addr_t size,
- ram_addr_t phys_offset)
+ ram_addr_t phys_offset, bool log_dirty)
{
KVMState *s = kvm_state;
ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
(start_addr + size <= mem->start_addr + mem->memory_size) &&
(phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
/* The new slot fits into the existing one and comes with
- * identical parameters - nothing to be done. */
+ * identical parameters - update flags and done. */
+ kvm_slot_dirty_pages_log_change(mem, log_dirty);
return;
}
mem->memory_size = old.memory_size;
mem->start_addr = old.start_addr;
mem->phys_offset = old.phys_offset;
- mem->flags = 0;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
mem->memory_size = start_addr - old.start_addr;
mem->start_addr = old.start_addr;
mem->phys_offset = old.phys_offset;
- mem->flags = 0;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
fprintf(stderr, "%s: error registering prefix slot: %s\n",
__func__, strerror(-err));
+#ifdef TARGET_PPC
+ fprintf(stderr, "%s: This is probably because your kernel's " \
+ "PAGE_SIZE is too big. Please try to use 4k " \
+ "PAGE_SIZE!\n", __func__);
+#endif
abort();
}
}
size_delta = mem->start_addr - old.start_addr;
mem->memory_size = old.memory_size - size_delta;
mem->phys_offset = old.phys_offset + size_delta;
- mem->flags = 0;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
mem->memory_size = size;
mem->start_addr = start_addr;
mem->phys_offset = phys_offset;
- mem->flags = 0;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
target_phys_addr_t start_addr,
- ram_addr_t size, ram_addr_t phys_offset)
+ ram_addr_t size, ram_addr_t phys_offset,
+ bool log_dirty)
{
- kvm_set_phys_mem(start_addr, size, phys_offset);
+ kvm_set_phys_mem(start_addr, size, phys_offset, log_dirty);
}
static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
.set_memory = kvm_client_set_memory,
.sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
.migration_log = kvm_client_migration_log,
+ .log_start = kvm_log_start,
+ .log_stop = kvm_log_stop,
};
-int kvm_init(int smp_cpus)
+static void kvm_handle_interrupt(CPUState *env, int mask)
+{
+ env->interrupt_request |= mask;
+
+ if (!qemu_cpu_is_self(env)) {
+ qemu_cpu_kick(env);
+ }
+}
+
+int kvm_init(void)
{
static const char upgrade_note[] =
"Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
"(see http://sourceforge.net/projects/kvm).\n";
KVMState *s;
+ const KVMCapabilityInfo *missing_cap;
int ret;
int i;
goto err;
}
- /* initially, KVM allocated its own memory and we had to jump through
- * hooks to make phys_ram_base point to this. Modern versions of KVM
- * just use a user allocated buffer so we can use regular pages
- * unmodified. Make sure we have a sufficiently modern version of KVM.
- */
- if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
- ret = -EINVAL;
- fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n%s",
- upgrade_note);
- goto err;
+ missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
+ if (!missing_cap) {
+ missing_cap =
+ kvm_check_extension_list(s, kvm_arch_required_capabilities);
}
-
- /* There was a nasty bug in < kvm-80 that prevents memory slots from being
- * destroyed properly. Since we rely on this capability, refuse to work
- * with any kernel without this capability. */
- if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
+ if (missing_cap) {
ret = -EINVAL;
-
- fprintf(stderr,
- "KVM kernel module broken (DESTROY_MEMORY_REGION).\n%s",
- upgrade_note);
+ fprintf(stderr, "kvm does not support %s\n%s",
+ missing_cap->name, upgrade_note);
goto err;
}
- s->coalesced_mmio = 0;
-#ifdef KVM_CAP_COALESCED_MMIO
s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
- s->coalesced_mmio_ring = NULL;
-#endif
s->broken_set_mem_region = 1;
-#ifdef KVM_CAP_JOIN_MEMORY_REGIONS_WORKS
ret = kvm_check_extension(s, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
if (ret > 0) {
s->broken_set_mem_region = 0;
}
-#endif
- s->vcpu_events = 0;
#ifdef KVM_CAP_VCPU_EVENTS
s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS);
#endif
- s->robust_singlestep = 0;
-#ifdef KVM_CAP_X86_ROBUST_SINGLESTEP
s->robust_singlestep =
kvm_check_extension(s, KVM_CAP_X86_ROBUST_SINGLESTEP);
-#endif
- s->debugregs = 0;
#ifdef KVM_CAP_DEBUGREGS
s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS);
#endif
- s->xsave = 0;
#ifdef KVM_CAP_XSAVE
s->xsave = kvm_check_extension(s, KVM_CAP_XSAVE);
#endif
- s->xcrs = 0;
#ifdef KVM_CAP_XCRS
s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
#endif
- ret = kvm_arch_init(s, smp_cpus);
+ ret = kvm_arch_init(s);
if (ret < 0) {
goto err;
}
s->many_ioeventfds = kvm_check_many_ioeventfds();
+ cpu_interrupt_handler = kvm_handle_interrupt;
+
return 0;
err:
return ret;
}
-static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
- uint32_t count)
+static void kvm_handle_io(uint16_t port, void *data, int direction, int size,
+ uint32_t count)
{
int i;
uint8_t *ptr = data;
ptr += size;
}
-
- return 1;
}
-#ifdef KVM_CAP_INTERNAL_ERROR_DATA
-static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
+static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
{
-
+ fprintf(stderr, "KVM internal error.");
if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
int i;
- fprintf(stderr, "KVM internal error. Suberror: %d\n",
- run->internal.suberror);
-
+ fprintf(stderr, " Suberror: %d\n", run->internal.suberror);
for (i = 0; i < run->internal.ndata; ++i) {
fprintf(stderr, "extra data[%d]: %"PRIx64"\n",
i, (uint64_t)run->internal.data[i]);
}
+ } else {
+ fprintf(stderr, "\n");
}
- cpu_dump_state(env, stderr, fprintf, 0);
if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
fprintf(stderr, "emulation failure\n");
if (!kvm_arch_stop_on_emulation_error(env)) {
- return;
+ cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ return EXCP_INTERRUPT;
}
}
/* FIXME: Should trigger a qmp message to let management know
* something went wrong.
*/
- vm_stop(0);
+ return -1;
}
-#endif
void kvm_flush_coalesced_mmio_buffer(void)
{
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio_ring) {
struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring;
ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
}
}
-#endif
}
static void do_kvm_cpu_synchronize_state(void *_env)
int kvm_cpu_exec(CPUState *env)
{
struct kvm_run *run = env->kvm_run;
- int ret;
+ int ret, run_ret;
DPRINTF("kvm_cpu_exec()\n");
- do {
-#ifndef CONFIG_IOTHREAD
- if (env->exit_request) {
- DPRINTF("interrupt exit requested\n");
- ret = 0;
- break;
- }
-#endif
+ if (kvm_arch_process_async_events(env)) {
+ env->exit_request = 0;
+ return EXCP_HLT;
+ }
- if (kvm_arch_process_irqchip_events(env)) {
- ret = 0;
- break;
- }
+ cpu_single_env = env;
+ do {
if (env->kvm_vcpu_dirty) {
kvm_arch_put_registers(env, KVM_PUT_RUNTIME_STATE);
env->kvm_vcpu_dirty = 0;
}
kvm_arch_pre_run(env, run);
+ if (env->exit_request) {
+ DPRINTF("interrupt exit requested\n");
+ /*
+ * KVM requires us to reenter the kernel after IO exits to complete
+ * instruction emulation. This self-signal will ensure that we
+ * leave ASAP again.
+ */
+ qemu_cpu_kick_self();
+ }
cpu_single_env = NULL;
qemu_mutex_unlock_iothread();
- ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+
+ run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+
qemu_mutex_lock_iothread();
cpu_single_env = env;
kvm_arch_post_run(env, run);
- if (ret == -EINTR || ret == -EAGAIN) {
- cpu_exit(env);
- DPRINTF("io window exit\n");
- ret = 0;
- break;
- }
+ kvm_flush_coalesced_mmio_buffer();
- if (ret < 0) {
- DPRINTF("kvm run failed %s\n", strerror(-ret));
+ if (run_ret < 0) {
+ if (run_ret == -EINTR || run_ret == -EAGAIN) {
+ DPRINTF("io window exit\n");
+ ret = EXCP_INTERRUPT;
+ break;
+ }
+ DPRINTF("kvm run failed %s\n", strerror(-run_ret));
abort();
}
- kvm_flush_coalesced_mmio_buffer();
-
- ret = 0; /* exit loop */
switch (run->exit_reason) {
case KVM_EXIT_IO:
DPRINTF("handle_io\n");
- ret = kvm_handle_io(run->io.port,
- (uint8_t *)run + run->io.data_offset,
- run->io.direction,
- run->io.size,
- run->io.count);
+ kvm_handle_io(run->io.port,
+ (uint8_t *)run + run->io.data_offset,
+ run->io.direction,
+ run->io.size,
+ run->io.count);
+ ret = 0;
break;
case KVM_EXIT_MMIO:
DPRINTF("handle_mmio\n");
run->mmio.data,
run->mmio.len,
run->mmio.is_write);
- ret = 1;
+ ret = 0;
break;
case KVM_EXIT_IRQ_WINDOW_OPEN:
DPRINTF("irq_window_open\n");
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_SHUTDOWN:
DPRINTF("shutdown\n");
qemu_system_reset_request();
- ret = 1;
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_UNKNOWN:
- DPRINTF("kvm_exit_unknown\n");
- break;
- case KVM_EXIT_FAIL_ENTRY:
- DPRINTF("kvm_exit_fail_entry\n");
- break;
- case KVM_EXIT_EXCEPTION:
- DPRINTF("kvm_exit_exception\n");
+ fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
+ (uint64_t)run->hw.hardware_exit_reason);
+ ret = -1;
break;
-#ifdef KVM_CAP_INTERNAL_ERROR_DATA
case KVM_EXIT_INTERNAL_ERROR:
- kvm_handle_internal_error(env, run);
- break;
-#endif
- case KVM_EXIT_DEBUG:
- DPRINTF("kvm_exit_debug\n");
-#ifdef KVM_CAP_SET_GUEST_DEBUG
- if (kvm_arch_debug(&run->debug.arch)) {
- env->exception_index = EXCP_DEBUG;
- return 0;
- }
- /* re-enter, this exception was guest-internal */
- ret = 1;
-#endif /* KVM_CAP_SET_GUEST_DEBUG */
+ ret = kvm_handle_internal_error(env, run);
break;
default:
DPRINTF("kvm_arch_handle_exit\n");
ret = kvm_arch_handle_exit(env, run);
break;
}
- } while (ret > 0);
+ } while (ret == 0);
- if (env->exit_request) {
- env->exit_request = 0;
- env->exception_index = EXCP_INTERRUPT;
+ if (ret < 0) {
+ cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ vm_stop(VMSTOP_PANIC);
}
+ env->exit_request = 0;
+ cpu_single_env = NULL;
return ret;
}
int kvm_has_sync_mmu(void)
{
-#ifdef KVM_CAP_SYNC_MMU
- KVMState *s = kvm_state;
-
- return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
-#else
- return 0;
-#endif
+ return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
}
int kvm_has_vcpu_events(void)
bp->use_count = 1;
err = kvm_arch_insert_sw_breakpoint(current_env, bp);
if (err) {
- free(bp);
+ qemu_free(bp);
return err;
}
sigmask->len = 8;
memcpy(sigmask->sigset, sigset, sizeof(*sigset));
r = kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, sigmask);
- free(sigmask);
+ qemu_free(sigmask);
return r;
}
return -ENOSYS;
#endif
}
+
+int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
+{
+ return kvm_arch_on_sigbus_vcpu(env, code, addr);
+}
+
+int kvm_on_sigbus(int code, void *addr)
+{
+ return kvm_arch_on_sigbus(code, addr);
+}
projects / qemu.git / blobdiff