#include "hw/pc.h"
#include "hw/apic.h"
#include "ioport.h"
+#include "hyperv.h"
//#define DEBUG_KVM
cpuid_i = 0;
/* Paravirtualization CPUIDs */
- memcpy(signature, "KVMKVMKVM\0\0\0", 12);
c = &cpuid_data.entries[cpuid_i++];
memset(c, 0, sizeof(*c));
c->function = KVM_CPUID_SIGNATURE;
- c->eax = 0;
+ if (!hyperv_enabled()) {
+ memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+ c->eax = 0;
+ } else {
+ memcpy(signature, "Microsoft Hv", 12);
+ c->eax = HYPERV_CPUID_MIN;
+ }
c->ebx = signature[0];
c->ecx = signature[1];
c->edx = signature[2];
c->eax = env->cpuid_kvm_features &
kvm_arch_get_supported_cpuid(s, KVM_CPUID_FEATURES, 0, R_EAX);
+ if (hyperv_enabled()) {
+ memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
+ c->eax = signature[0];
+
+ c = &cpuid_data.entries[cpuid_i++];
+ memset(c, 0, sizeof(*c));
+ c->function = HYPERV_CPUID_VERSION;
+ c->eax = 0x00001bbc;
+ c->ebx = 0x00060001;
+
+ c = &cpuid_data.entries[cpuid_i++];
+ memset(c, 0, sizeof(*c));
+ c->function = HYPERV_CPUID_FEATURES;
+ if (hyperv_relaxed_timing_enabled()) {
+ c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+ }
+ if (hyperv_vapic_recommended()) {
+ c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+ c->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE;
+ }
+
+ c = &cpuid_data.entries[cpuid_i++];
+ memset(c, 0, sizeof(*c));
+ c->function = HYPERV_CPUID_ENLIGHTMENT_INFO;
+ if (hyperv_relaxed_timing_enabled()) {
+ c->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
+ }
+ if (hyperv_vapic_recommended()) {
+ c->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
+ }
+ c->ebx = hyperv_get_spinlock_retries();
+
+ c = &cpuid_data.entries[cpuid_i++];
+ memset(c, 0, sizeof(*c));
+ c->function = HYPERV_CPUID_IMPLEMENT_LIMITS;
+ c->eax = 0x40;
+ c->ebx = 0x40;
+
+ c = &cpuid_data.entries[cpuid_i++];
+ memset(c, 0, sizeof(*c));
+ c->function = KVM_CPUID_SIGNATURE_NEXT;
+ memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+ c->eax = 0;
+ c->ebx = signature[0];
+ c->ecx = signature[1];
+ c->edx = signature[2];
+ }
+
has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);
cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);
}
}
+ if (kvm_has_xsave()) {
+ env->kvm_xsave_buf = qemu_memalign(4096, sizeof(struct kvm_xsave));
+ }
+
return 0;
}
int kvm_arch_init(KVMState *s)
{
+ QemuOptsList *list = qemu_find_opts("machine");
uint64_t identity_base = 0xfffbc000;
+ uint64_t shadow_mem;
int ret;
struct utsname utsname;
}
qemu_register_reset(kvm_unpoison_all, NULL);
+ if (!QTAILQ_EMPTY(&list->head)) {
+ shadow_mem = qemu_opt_get_size(QTAILQ_FIRST(&list->head),
+ "kvm_shadow_mem", -1);
+ if (shadow_mem != -1) {
+ shadow_mem /= 4096;
+ ret = kvm_vm_ioctl(s, KVM_SET_NR_MMU_PAGES, shadow_mem);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+ }
return 0;
}
return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
}
+#define XSAVE_FCW_FSW 0
+#define XSAVE_FTW_FOP 1
#define XSAVE_CWD_RIP 2
#define XSAVE_CWD_RDP 4
#define XSAVE_MXCSR 6
static int kvm_put_xsave(CPUState *env)
{
- int i, r;
- struct kvm_xsave* xsave;
+ struct kvm_xsave* xsave = env->kvm_xsave_buf;
uint16_t cwd, swd, twd;
+ int i, r;
if (!kvm_has_xsave()) {
return kvm_put_fpu(env);
}
- xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
memset(xsave, 0, sizeof(struct kvm_xsave));
twd = 0;
swd = env->fpus & ~(7 << 11);
for (i = 0; i < 8; ++i) {
twd |= (!env->fptags[i]) << i;
}
- xsave->region[0] = (uint32_t)(swd << 16) + cwd;
- xsave->region[1] = (uint32_t)(env->fpop << 16) + twd;
+ xsave->region[XSAVE_FCW_FSW] = (uint32_t)(swd << 16) + cwd;
+ xsave->region[XSAVE_FTW_FOP] = (uint32_t)(env->fpop << 16) + twd;
memcpy(&xsave->region[XSAVE_CWD_RIP], &env->fpip, sizeof(env->fpip));
memcpy(&xsave->region[XSAVE_CWD_RDP], &env->fpdp, sizeof(env->fpdp));
memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
sizeof env->ymmh_regs);
r = kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
- g_free(xsave);
return r;
}
kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN,
env->async_pf_en_msr);
}
+ if (hyperv_hypercall_available()) {
+ kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_GUEST_OS_ID, 0);
+ kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_HYPERCALL, 0);
+ }
+ if (hyperv_vapic_recommended()) {
+ kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_APIC_ASSIST_PAGE, 0);
+ }
}
if (env->mcg_cap) {
int i;
static int kvm_get_xsave(CPUState *env)
{
- struct kvm_xsave* xsave;
+ struct kvm_xsave* xsave = env->kvm_xsave_buf;
int ret, i;
uint16_t cwd, swd, twd;
return kvm_get_fpu(env);
}
- xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
if (ret < 0) {
- g_free(xsave);
return ret;
}
- cwd = (uint16_t)xsave->region[0];
- swd = (uint16_t)(xsave->region[0] >> 16);
- twd = (uint16_t)xsave->region[1];
- env->fpop = (uint16_t)(xsave->region[1] >> 16);
+ cwd = (uint16_t)xsave->region[XSAVE_FCW_FSW];
+ swd = (uint16_t)(xsave->region[XSAVE_FCW_FSW] >> 16);
+ twd = (uint16_t)xsave->region[XSAVE_FTW_FOP];
+ env->fpop = (uint16_t)(xsave->region[XSAVE_FTW_FOP] >> 16);
env->fpstt = (swd >> 11) & 7;
env->fpus = swd;
env->fpuc = cwd;
env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
sizeof env->ymmh_regs);
- g_free(xsave);
return 0;
}
env->cr[3] = sregs.cr3;
env->cr[4] = sregs.cr4;
- cpu_set_apic_base(env->apic_state, sregs.apic_base);
-
env->efer = sregs.efer;
- //cpu_set_apic_tpr(env->apic_state, sregs.cr8);
+
+ /* changes to apic base and cr8/tpr are read back via kvm_arch_post_run */
#define HFLAG_COPY_MASK \
~( HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \
return 0;
}
+static int kvm_get_apic(CPUState *env)
+{
+ DeviceState *apic = env->apic_state;
+ struct kvm_lapic_state kapic;
+ int ret;
+
+ if (apic && kvm_irqchip_in_kernel()) {
+ ret = kvm_vcpu_ioctl(env, KVM_GET_LAPIC, &kapic);
+ if (ret < 0) {
+ return ret;
+ }
+
+ kvm_get_apic_state(apic, &kapic);
+ }
+ return 0;
+}
+
+static int kvm_put_apic(CPUState *env)
+{
+ DeviceState *apic = env->apic_state;
+ struct kvm_lapic_state kapic;
+
+ if (apic && kvm_irqchip_in_kernel()) {
+ kvm_put_apic_state(apic, &kapic);
+
+ return kvm_vcpu_ioctl(env, KVM_SET_LAPIC, &kapic);
+ }
+ return 0;
+}
+
static int kvm_put_vcpu_events(CPUState *env, int level)
{
struct kvm_vcpu_events events;
if (ret < 0) {
return ret;
}
+ ret = kvm_put_apic(env);
+ if (ret < 0) {
+ return ret;
+ }
}
ret = kvm_put_vcpu_events(env, level);
if (ret < 0) {
if (ret < 0) {
return ret;
}
+ ret = kvm_get_apic(env);
+ if (ret < 0) {
+ return ret;
+ }
ret = kvm_get_vcpu_events(env);
if (ret < 0) {
return ret;
}
if (!kvm_irqchip_in_kernel()) {
- /* Force the VCPU out of its inner loop to process the INIT request */
- if (env->interrupt_request & CPU_INTERRUPT_INIT) {
+ /* Force the VCPU out of its inner loop to process any INIT requests
+ * or pending TPR access reports. */
+ if (env->interrupt_request &
+ (CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR)) {
env->exit_request = 1;
}
kvm_cpu_synchronize_state(env);
do_cpu_sipi(env);
}
+ if (env->interrupt_request & CPU_INTERRUPT_TPR) {
+ env->interrupt_request &= ~CPU_INTERRUPT_TPR;
+ kvm_cpu_synchronize_state(env);
+ apic_handle_tpr_access_report(env->apic_state, env->eip,
+ env->tpr_access_type);
+ }
return env->halted;
}
return 0;
}
+static int kvm_handle_tpr_access(CPUState *env)
+{
+ struct kvm_run *run = env->kvm_run;
+
+ apic_handle_tpr_access_report(env->apic_state, run->tpr_access.rip,
+ run->tpr_access.is_write ? TPR_ACCESS_WRITE
+ : TPR_ACCESS_READ);
+ return 1;
+}
+
int kvm_arch_insert_sw_breakpoint(CPUState *env, struct kvm_sw_breakpoint *bp)
{
static const uint8_t int3 = 0xcc;
case KVM_EXIT_SET_TPR:
ret = 0;
break;
+ case KVM_EXIT_TPR_ACCESS:
+ ret = kvm_handle_tpr_access(env);
+ break;
case KVM_EXIT_FAIL_ENTRY:
code = run->fail_entry.hardware_entry_failure_reason;
fprintf(stderr, "KVM: entry failed, hardware error 0x%" PRIx64 "\n",
bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
+ kvm_cpu_synchronize_state(env);
return !(env->cr[0] & CR0_PE_MASK) ||
((env->segs[R_CS].selector & 3) != 3);
}
+
+void kvm_arch_init_irq_routing(KVMState *s)
+{
+ if (!kvm_check_extension(s, KVM_CAP_IRQ_ROUTING)) {
+ /* If kernel can't do irq routing, interrupt source
+ * override 0->2 cannot be set up as required by HPET.
+ * So we have to disable it.
+ */
+ no_hpet = 1;
+ }
+}