*
*/
-#include <sys/types.h>
+#include "qemu/osdep.h"
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/utsname.h>
#include "exec/ioport.h"
#include "standard-headers/asm-x86/hyperv.h"
#include "hw/pci/pci.h"
+#include "hw/pci/msi.h"
#include "migration/migration.h"
#include "exec/memattrs.h"
cpu->hyperv_stimer);
}
+static int kvm_arch_set_tsc_khz(CPUState *cs)
+{
+ X86CPU *cpu = X86_CPU(cs);
+ CPUX86State *env = &cpu->env;
+ int r;
+
+ if (!env->tsc_khz) {
+ return 0;
+ }
+
+ r = kvm_check_extension(cs->kvm_state, KVM_CAP_TSC_CONTROL) ?
+ kvm_vcpu_ioctl(cs, KVM_SET_TSC_KHZ, env->tsc_khz) :
+ -ENOTSUP;
+ if (r < 0) {
+ /* When KVM_SET_TSC_KHZ fails, it's an error only if the current
+ * TSC frequency doesn't match the one we want.
+ */
+ int cur_freq = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
+ kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
+ -ENOTSUP;
+ if (cur_freq <= 0 || cur_freq != env->tsc_khz) {
+ error_report("warning: TSC frequency mismatch between "
+ "VM and host, and TSC scaling unavailable");
+ return r;
+ }
+ }
+
+ return 0;
+}
+
static Error *invtsc_mig_blocker;
#define KVM_MAX_CPUID_ENTRIES 100
return r;
}
- r = kvm_check_extension(cs->kvm_state, KVM_CAP_TSC_CONTROL);
- if (r && env->tsc_khz) {
- r = kvm_vcpu_ioctl(cs, KVM_SET_TSC_KHZ, env->tsc_khz);
- if (r < 0) {
- fprintf(stderr, "KVM_SET_TSC_KHZ failed\n");
- return r;
+ r = kvm_arch_set_tsc_khz(cs);
+ if (r < 0) {
+ return r;
+ }
+
+ /* vcpu's TSC frequency is either specified by user, or following
+ * the value used by KVM if the former is not present. In the
+ * latter case, we query it from KVM and record in env->tsc_khz,
+ * so that vcpu's TSC frequency can be migrated later via this field.
+ */
+ if (!env->tsc_khz) {
+ r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
+ kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
+ -ENOTSUP;
+ if (r > 0) {
+ env->tsc_khz = r;
}
}
lhs->l = (flags >> DESC_L_SHIFT) & 1;
lhs->g = (flags & DESC_G_MASK) != 0;
lhs->avl = (flags & DESC_AVL_MASK) != 0;
- lhs->unusable = 0;
+ lhs->unusable = !lhs->present;
lhs->padding = 0;
}
lhs->selector = rhs->selector;
lhs->base = rhs->base;
lhs->limit = rhs->limit;
- lhs->flags = (rhs->type << DESC_TYPE_SHIFT) |
- (rhs->present * DESC_P_MASK) |
- (rhs->dpl << DESC_DPL_SHIFT) |
- (rhs->db << DESC_B_SHIFT) |
- (rhs->s * DESC_S_MASK) |
- (rhs->l << DESC_L_SHIFT) |
- (rhs->g * DESC_G_MASK) |
- (rhs->avl * DESC_AVL_MASK);
+ if (rhs->unusable) {
+ lhs->flags = 0;
+ } else {
+ lhs->flags = (rhs->type << DESC_TYPE_SHIFT) |
+ (rhs->present * DESC_P_MASK) |
+ (rhs->dpl << DESC_DPL_SHIFT) |
+ (rhs->db << DESC_B_SHIFT) |
+ (rhs->s * DESC_S_MASK) |
+ (rhs->l << DESC_L_SHIFT) |
+ (rhs->g * DESC_G_MASK) |
+ (rhs->avl * DESC_AVL_MASK);
+ }
}
static void kvm_getput_reg(__u64 *kvm_reg, target_ulong *qemu_reg, int set)
}
memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
for (i = 0; i < CPU_NB_REGS; i++) {
- stq_p(&fpu.xmm[i][0], env->xmm_regs[i].XMM_Q(0));
- stq_p(&fpu.xmm[i][8], env->xmm_regs[i].XMM_Q(1));
+ stq_p(&fpu.xmm[i][0], env->xmm_regs[i].ZMM_Q(0));
+ stq_p(&fpu.xmm[i][8], env->xmm_regs[i].ZMM_Q(1));
}
fpu.mxcsr = env->mxcsr;
#define XSAVE_OPMASK 272
#define XSAVE_ZMM_Hi256 288
#define XSAVE_Hi16_ZMM 416
+#define XSAVE_PKRU 672
static int kvm_put_xsave(X86CPU *cpu)
{
ymmh = (uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
zmmh = (uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
- stq_p(xmm, env->xmm_regs[i].XMM_Q(0));
- stq_p(xmm+8, env->xmm_regs[i].XMM_Q(1));
- stq_p(ymmh, env->xmm_regs[i].XMM_Q(2));
- stq_p(ymmh+8, env->xmm_regs[i].XMM_Q(3));
- stq_p(zmmh, env->xmm_regs[i].XMM_Q(4));
- stq_p(zmmh+8, env->xmm_regs[i].XMM_Q(5));
- stq_p(zmmh+16, env->xmm_regs[i].XMM_Q(6));
- stq_p(zmmh+24, env->xmm_regs[i].XMM_Q(7));
+ stq_p(xmm, env->xmm_regs[i].ZMM_Q(0));
+ stq_p(xmm+8, env->xmm_regs[i].ZMM_Q(1));
+ stq_p(ymmh, env->xmm_regs[i].ZMM_Q(2));
+ stq_p(ymmh+8, env->xmm_regs[i].ZMM_Q(3));
+ stq_p(zmmh, env->xmm_regs[i].ZMM_Q(4));
+ stq_p(zmmh+8, env->xmm_regs[i].ZMM_Q(5));
+ stq_p(zmmh+16, env->xmm_regs[i].ZMM_Q(6));
+ stq_p(zmmh+24, env->xmm_regs[i].ZMM_Q(7));
}
#ifdef TARGET_X86_64
memcpy(&xsave->region[XSAVE_Hi16_ZMM], &env->xmm_regs[16],
16 * sizeof env->xmm_regs[16]);
+ memcpy(&xsave->region[XSAVE_PKRU], &env->pkru, sizeof env->pkru);
#endif
r = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_XSAVE, xsave);
return r;
}
memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
for (i = 0; i < CPU_NB_REGS; i++) {
- env->xmm_regs[i].XMM_Q(0) = ldq_p(&fpu.xmm[i][0]);
- env->xmm_regs[i].XMM_Q(1) = ldq_p(&fpu.xmm[i][8]);
+ env->xmm_regs[i].ZMM_Q(0) = ldq_p(&fpu.xmm[i][0]);
+ env->xmm_regs[i].ZMM_Q(1) = ldq_p(&fpu.xmm[i][8]);
}
env->mxcsr = fpu.mxcsr;
ymmh = (const uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
zmmh = (const uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
- env->xmm_regs[i].XMM_Q(0) = ldq_p(xmm);
- env->xmm_regs[i].XMM_Q(1) = ldq_p(xmm+8);
- env->xmm_regs[i].XMM_Q(2) = ldq_p(ymmh);
- env->xmm_regs[i].XMM_Q(3) = ldq_p(ymmh+8);
- env->xmm_regs[i].XMM_Q(4) = ldq_p(zmmh);
- env->xmm_regs[i].XMM_Q(5) = ldq_p(zmmh+8);
- env->xmm_regs[i].XMM_Q(6) = ldq_p(zmmh+16);
- env->xmm_regs[i].XMM_Q(7) = ldq_p(zmmh+24);
+ env->xmm_regs[i].ZMM_Q(0) = ldq_p(xmm);
+ env->xmm_regs[i].ZMM_Q(1) = ldq_p(xmm+8);
+ env->xmm_regs[i].ZMM_Q(2) = ldq_p(ymmh);
+ env->xmm_regs[i].ZMM_Q(3) = ldq_p(ymmh+8);
+ env->xmm_regs[i].ZMM_Q(4) = ldq_p(zmmh);
+ env->xmm_regs[i].ZMM_Q(5) = ldq_p(zmmh+8);
+ env->xmm_regs[i].ZMM_Q(6) = ldq_p(zmmh+16);
+ env->xmm_regs[i].ZMM_Q(7) = ldq_p(zmmh+24);
}
#ifdef TARGET_X86_64
memcpy(&env->xmm_regs[16], &xsave->region[XSAVE_Hi16_ZMM],
16 * sizeof env->xmm_regs[16]);
+ memcpy(&env->pkru, &xsave->region[XSAVE_PKRU], sizeof env->pkru);
#endif
return 0;
}
HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \
HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)
- hflags = (env->segs[R_SS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
+ hflags = env->hflags & HFLAG_COPY_MASK;
+ hflags |= (env->segs[R_SS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT);
hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) &
(HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);
hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK));
- hflags |= (env->cr[4] & CR4_OSFXSR_MASK) <<
- (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT);
+
+ if (env->cr[4] & CR4_OSFXSR_MASK) {
+ hflags |= HF_OSFXSR_MASK;
+ }
if (env->efer & MSR_EFER_LMA) {
hflags |= HF_LMA_MASK;
env->segs[R_SS].base) != 0) << HF_ADDSEG_SHIFT;
}
}
- env->hflags = (env->hflags & HFLAG_COPY_MASK) | hflags;
+ env->hflags = hflags;
return 0;
}
}
}
+ if (level == KVM_PUT_FULL_STATE) {
+ /* We don't check for kvm_arch_set_tsc_khz() errors here,
+ * because TSC frequency mismatch shouldn't abort migration,
+ * unless the user explicitly asked for a more strict TSC
+ * setting (e.g. using an explicit "tsc-freq" option).
+ */
+ kvm_arch_set_tsc_khz(cpu);
+ }
+
ret = kvm_getput_regs(x86_cpu, 1);
if (ret < 0) {
return ret;
ret = kvm_getput_regs(cpu, 0);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_xsave(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_xcrs(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_sregs(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_msrs(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_mp_state(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_apic(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_vcpu_events(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
ret = kvm_get_debugregs(cpu);
if (ret < 0) {
- return ret;
+ goto out;
}
- return 0;
+ ret = 0;
+ out:
+ cpu_sync_bndcs_hflags(&cpu->env);
+ return ret;
}
void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
}
}
- if (!kvm_irqchip_in_kernel()) {
+ if (!kvm_pic_in_kernel()) {
qemu_mutex_lock_iothread();
}
}
}
- if (!kvm_irqchip_in_kernel()) {
+ if (!kvm_pic_in_kernel()) {
/* Try to inject an interrupt if the guest can accept it */
if (run->ready_for_interrupt_injection &&
(cpu->interrupt_request & CPU_INTERRUPT_HARD) &&
case KVM_EXIT_HYPERV:
ret = kvm_hv_handle_exit(cpu, &run->hyperv);
break;
+ case KVM_EXIT_IOAPIC_EOI:
+ ioapic_eoi_broadcast(run->eoi.vector);
+ ret = 0;
+ break;
default:
fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
ret = -1;
*/
kvm_msi_via_irqfd_allowed = true;
kvm_gsi_routing_allowed = true;
+
+ if (kvm_irqchip_is_split()) {
+ int i;
+
+ /* If the ioapic is in QEMU and the lapics are in KVM, reserve
+ MSI routes for signaling interrupts to the local apics. */
+ for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+ struct MSIMessage msg = { 0x0, 0x0 };
+ if (kvm_irqchip_add_msi_route(s, msg, NULL) < 0) {
+ error_report("Could not enable split IRQ mode.");
+ exit(1);
+ }
+ }
+ }
+}
+
+int kvm_arch_irqchip_create(MachineState *ms, KVMState *s)
+{
+ int ret;
+ if (machine_kernel_irqchip_split(ms)) {
+ ret = kvm_vm_enable_cap(s, KVM_CAP_SPLIT_IRQCHIP, 0, 24);
+ if (ret) {
+ error_report("Could not enable split irqchip mode: %s\n",
+ strerror(-ret));
+ exit(1);
+ } else {
+ DPRINTF("Enabled KVM_CAP_SPLIT_IRQCHIP\n");
+ kvm_split_irqchip = true;
+ return 1;
+ }
+ } else {
+ return 0;
+ }
}
/* Classic KVM device assignment interface. Will remain x86 only. */
projects / qemu.git / blobdiff