#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
+#include <asm/mshyperv.h>
+#include <asm/hypervisor.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
static void process_nmi(struct kvm_vcpu *vcpu);
static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+static void store_regs(struct kvm_vcpu *vcpu);
+static int sync_regs(struct kvm_vcpu *vcpu);
struct kvm_x86_ops *kvm_x86_ops __read_mostly;
EXPORT_SYMBOL_GPL(kvm_x86_ops);
{ "request_irq", VCPU_STAT(request_irq_exits) },
{ "irq_exits", VCPU_STAT(irq_exits) },
{ "host_state_reload", VCPU_STAT(host_state_reload) },
- { "efer_reload", VCPU_STAT(efer_reload) },
{ "fpu_reload", VCPU_STAT(fpu_reload) },
{ "insn_emulation", VCPU_STAT(insn_emulation) },
{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
/* kvm_set_xcr() also depends on this */
- xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
+ if (vcpu->arch.xcr0 != host_xcr0)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
vcpu->guest_xcr0_loaded = 1;
}
}
if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
return 1;
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+ return 1;
+
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE))
return 1;
HV_X64_MSR_VP_RUNTIME,
HV_X64_MSR_SCONTROL,
HV_X64_MSR_STIMER0_CONFIG,
- HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
+ HV_X64_MSR_APIC_ASSIST_PAGE,
+ HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL,
+ HV_X64_MSR_TSC_EMULATION_STATUS,
+
+ MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
MSR_KVM_PV_EOI_EN,
MSR_IA32_TSC_ADJUST,
MSR_IA32_MCG_CTL,
MSR_IA32_MCG_EXT_CTL,
MSR_IA32_SMBASE,
+ MSR_SMI_COUNT,
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
};
static unsigned num_emulated_msrs;
+/*
+ * List of msr numbers which are used to expose MSR-based features that
+ * can be used by a hypervisor to validate requested CPU features.
+ */
+static u32 msr_based_features[] = {
+ MSR_IA32_VMX_BASIC,
+ MSR_IA32_VMX_TRUE_PINBASED_CTLS,
+ MSR_IA32_VMX_PINBASED_CTLS,
+ MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
+ MSR_IA32_VMX_PROCBASED_CTLS,
+ MSR_IA32_VMX_TRUE_EXIT_CTLS,
+ MSR_IA32_VMX_EXIT_CTLS,
+ MSR_IA32_VMX_TRUE_ENTRY_CTLS,
+ MSR_IA32_VMX_ENTRY_CTLS,
+ MSR_IA32_VMX_MISC,
+ MSR_IA32_VMX_CR0_FIXED0,
+ MSR_IA32_VMX_CR0_FIXED1,
+ MSR_IA32_VMX_CR4_FIXED0,
+ MSR_IA32_VMX_CR4_FIXED1,
+ MSR_IA32_VMX_VMCS_ENUM,
+ MSR_IA32_VMX_PROCBASED_CTLS2,
+ MSR_IA32_VMX_EPT_VPID_CAP,
+ MSR_IA32_VMX_VMFUNC,
+
+ MSR_F10H_DECFG,
+ MSR_IA32_UCODE_REV,
+};
+
+static unsigned int num_msr_based_features;
+
+static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+ switch (msr->index) {
+ case MSR_IA32_UCODE_REV:
+ rdmsrl(msr->index, msr->data);
+ break;
+ default:
+ if (kvm_x86_ops->get_msr_feature(msr))
+ return 1;
+ }
+ return 0;
+}
+
+static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
+{
+ struct kvm_msr_entry msr;
+ int r;
+
+ msr.index = index;
+ r = kvm_get_msr_feature(&msr);
+ if (r)
+ return r;
+
+ *data = msr.data;
+
+ return 0;
+}
+
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
if (efer & efer_reserved_bits)
return tsc;
}
+static inline int gtod_is_based_on_tsc(int mode)
+{
+ return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK;
+}
+
static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
* perform request to enable masterclock.
*/
if (ka->use_master_clock ||
- (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
+ (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
vcpu->arch.tsc_offset = offset;
}
+static inline bool kvm_check_tsc_unstable(void)
+{
+#ifdef CONFIG_X86_64
+ /*
+ * TSC is marked unstable when we're running on Hyper-V,
+ * 'TSC page' clocksource is good.
+ */
+ if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK)
+ return false;
+#endif
+ return check_tsc_unstable();
+}
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct kvm *kvm = vcpu->kvm;
*/
if (synchronizing &&
vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
- if (!check_tsc_unstable()) {
+ if (!kvm_check_tsc_unstable()) {
offset = kvm->arch.cur_tsc_offset;
pr_debug("kvm: matched tsc offset for %llu\n", data);
} else {
return last;
}
-static inline u64 vgettsc(u64 *cycle_now)
+static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
{
long v;
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+ u64 tsc_pg_val;
+
+ switch (gtod->clock.vclock_mode) {
+ case VCLOCK_HVCLOCK:
+ tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
+ tsc_timestamp);
+ if (tsc_pg_val != U64_MAX) {
+ /* TSC page valid */
+ *mode = VCLOCK_HVCLOCK;
+ v = (tsc_pg_val - gtod->clock.cycle_last) &
+ gtod->clock.mask;
+ } else {
+ /* TSC page invalid */
+ *mode = VCLOCK_NONE;
+ }
+ break;
+ case VCLOCK_TSC:
+ *mode = VCLOCK_TSC;
+ *tsc_timestamp = read_tsc();
+ v = (*tsc_timestamp - gtod->clock.cycle_last) &
+ gtod->clock.mask;
+ break;
+ default:
+ *mode = VCLOCK_NONE;
+ }
- *cycle_now = read_tsc();
+ if (*mode == VCLOCK_NONE)
+ *tsc_timestamp = v = 0;
- v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask;
return v * gtod->clock.mult;
}
-static int do_monotonic_boot(s64 *t, u64 *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
{
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
unsigned long seq;
do {
seq = read_seqcount_begin(>od->seq);
- mode = gtod->clock.vclock_mode;
ns = gtod->nsec_base;
- ns += vgettsc(cycle_now);
+ ns += vgettsc(tsc_timestamp, &mode);
ns >>= gtod->clock.shift;
ns += gtod->boot_ns;
} while (unlikely(read_seqcount_retry(>od->seq, seq)));
return mode;
}
-static int do_realtime(struct timespec *ts, u64 *cycle_now)
+static int do_realtime(struct timespec *ts, u64 *tsc_timestamp)
{
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
unsigned long seq;
do {
seq = read_seqcount_begin(>od->seq);
- mode = gtod->clock.vclock_mode;
ts->tv_sec = gtod->wall_time_sec;
ns = gtod->nsec_base;
- ns += vgettsc(cycle_now);
+ ns += vgettsc(tsc_timestamp, &mode);
ns >>= gtod->clock.shift;
} while (unlikely(read_seqcount_retry(>od->seq, seq)));
return mode;
}
-/* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
+/* returns true if host is using TSC based clocksource */
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
{
/* checked again under seqlock below */
- if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
return false;
- return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
+ return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+ tsc_timestamp));
}
-/* returns true if host is using tsc clocksource */
+/* returns true if host is using TSC based clocksource */
static bool kvm_get_walltime_and_clockread(struct timespec *ts,
- u64 *cycle_now)
+ u64 *tsc_timestamp)
{
/* checked again under seqlock below */
- if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
return false;
- return do_realtime(ts, cycle_now) == VCLOCK_TSC;
+ return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
}
#endif
vcpu->arch.pv_time_enabled = false;
}
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
+{
+ ++vcpu->stat.tlb_flush;
+ kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
+}
+
static void record_steal_time(struct kvm_vcpu *vcpu)
{
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.preempted = 0;
+ /*
+ * Doing a TLB flush here, on the guest's behalf, can avoid
+ * expensive IPIs.
+ */
+ if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+ kvm_vcpu_flush_tlb(vcpu, false);
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
switch (msr) {
case MSR_AMD64_NB_CFG:
- case MSR_IA32_UCODE_REV:
case MSR_IA32_UCODE_WRITE:
case MSR_VM_HSAVE_PA:
case MSR_AMD64_PATCH_LOADER:
case MSR_AMD64_DC_CFG:
break;
+ case MSR_IA32_UCODE_REV:
+ if (msr_info->host_initiated)
+ vcpu->arch.microcode_version = data;
+ break;
case MSR_EFER:
return set_efer(vcpu, data);
case MSR_K7_HWCR:
return 1;
vcpu->arch.smbase = data;
break;
+ case MSR_SMI_COUNT:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.smi_count = data;
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
case HV_X64_MSR_CRASH_CTL:
case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
+ case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_STATUS:
return kvm_hv_set_msr_common(vcpu, msr, data,
msr_info->host_initiated);
case MSR_IA32_BBL_CR_CTL3:
case MSR_AMD64_DC_CFG:
msr_info->data = 0;
break;
+ case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
msr_info->data = 0;
break;
case MSR_IA32_UCODE_REV:
- msr_info->data = 0x100000000ULL;
+ msr_info->data = vcpu->arch.microcode_version;
break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return 1;
msr_info->data = vcpu->arch.smbase;
break;
+ case MSR_SMI_COUNT:
+ msr_info->data = vcpu->arch.smi_count;
+ break;
case MSR_IA32_PERF_STATUS:
/* TSC increment by tick */
msr_info->data = 1000ULL;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
case HV_X64_MSR_CRASH_CTL:
case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
+ case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_STATUS:
return kvm_hv_get_msr_common(vcpu,
msr_info->index, &msr_info->data);
break;
int (*do_msr)(struct kvm_vcpu *vcpu,
unsigned index, u64 *data))
{
- int i, idx;
+ int i;
- idx = srcu_read_lock(&vcpu->kvm->srcu);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
return i;
}
case KVM_CAP_HYPERV_SYNIC:
case KVM_CAP_HYPERV_SYNIC2:
case KVM_CAP_HYPERV_VP_INDEX:
+ case KVM_CAP_HYPERV_EVENTFD:
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
case KVM_CAP_SET_BOOT_CPU_ID:
case KVM_CAP_SPLIT_IRQCHIP:
case KVM_CAP_IMMEDIATE_EXIT:
+ case KVM_CAP_GET_MSR_FEATURES:
r = 1;
break;
+ case KVM_CAP_SYNC_REGS:
+ r = KVM_SYNC_X86_VALID_FIELDS;
+ break;
case KVM_CAP_ADJUST_CLOCK:
r = KVM_CLOCK_TSC_STABLE;
break;
goto out;
r = 0;
break;
+ case KVM_GET_MSR_FEATURE_INDEX_LIST: {
+ struct kvm_msr_list __user *user_msr_list = argp;
+ struct kvm_msr_list msr_list;
+ unsigned int n;
+
+ r = -EFAULT;
+ if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
+ goto out;
+ n = msr_list.nmsrs;
+ msr_list.nmsrs = num_msr_based_features;
+ if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
+ goto out;
+ r = -E2BIG;
+ if (n < msr_list.nmsrs)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(user_msr_list->indices, &msr_based_features,
+ num_msr_based_features * sizeof(u32)))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_GET_MSRS:
+ r = msr_io(NULL, argp, do_get_msr_feature, 1);
+ break;
}
default:
r = -EINVAL;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
}
- if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+ if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
rdtsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (check_tsc_unstable()) {
+ if (kvm_check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_vcpu_write_tsc_offset(vcpu, offset);
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
- vcpu->arch.st.steal.preempted = 1;
+ vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal.preempted,
pagefault_enable();
kvm_x86_ops->vcpu_put(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
+ /*
+ * If userspace has set any breakpoints or watchpoints, dr6 is restored
+ * on every vmexit, but if not, we might have a stale dr6 from the
+ * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+ */
+ set_debugreg(0, 6);
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
+ if (vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
return kvm_apic_get_state(vcpu, s);
void *buffer;
} u;
+ vcpu_load(vcpu);
+
u.buffer = NULL;
switch (ioctl) {
case KVM_GET_LAPIC: {
if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
- if (IS_ERR(u.lapic))
- return PTR_ERR(u.lapic);
+ if (IS_ERR(u.lapic)) {
+ r = PTR_ERR(u.lapic);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
break;
r = 0;
break;
}
- case KVM_GET_MSRS:
+ case KVM_GET_MSRS: {
+ int idx = srcu_read_lock(&vcpu->kvm->srcu);
r = msr_io(vcpu, argp, do_get_msr, 1);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
- case KVM_SET_MSRS:
+ }
+ case KVM_SET_MSRS: {
+ int idx = srcu_read_lock(&vcpu->kvm->srcu);
r = msr_io(vcpu, argp, do_set_msr, 0);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
+ }
case KVM_TPR_ACCESS_REPORTING: {
struct kvm_tpr_access_ctl tac;
}
case KVM_SET_XSAVE: {
u.xsave = memdup_user(argp, sizeof(*u.xsave));
- if (IS_ERR(u.xsave))
- return PTR_ERR(u.xsave);
+ if (IS_ERR(u.xsave)) {
+ r = PTR_ERR(u.xsave);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
break;
}
case KVM_SET_XCRS: {
u.xcrs = memdup_user(argp, sizeof(*u.xcrs));
- if (IS_ERR(u.xcrs))
- return PTR_ERR(u.xcrs);
+ if (IS_ERR(u.xcrs)) {
+ r = PTR_ERR(u.xcrs);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
break;
}
out:
kfree(u.buffer);
+out_nofree:
+ vcpu_put(vcpu);
return r;
}
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
+ case KVM_MEMORY_ENCRYPT_OP: {
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_op)
+ r = kvm_x86_ops->mem_enc_op(kvm, argp);
+ break;
+ }
+ case KVM_MEMORY_ENCRYPT_REG_REGION: {
+ struct kvm_enc_region region;
+
+ r = -EFAULT;
+ if (copy_from_user(®ion, argp, sizeof(region)))
+ goto out;
+
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_reg_region)
+ r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion);
+ break;
+ }
+ case KVM_MEMORY_ENCRYPT_UNREG_REGION: {
+ struct kvm_enc_region region;
+
+ r = -EFAULT;
+ if (copy_from_user(®ion, argp, sizeof(region)))
+ goto out;
+
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_unreg_region)
+ r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion);
+ break;
+ }
+ case KVM_HYPERV_EVENTFD: {
+ struct kvm_hyperv_eventfd hvevfd;
+
+ r = -EFAULT;
+ if (copy_from_user(&hvevfd, argp, sizeof(hvevfd)))
+ goto out;
+ r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
+ break;
+ }
default:
r = -ENOTTY;
}
j++;
}
num_emulated_msrs = j;
+
+ for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+ struct kvm_msr_entry msr;
+
+ msr.index = msr_based_features[i];
+ if (kvm_get_msr_feature(&msr))
+ continue;
+
+ if (j < i)
+ msr_based_features[j] = msr_based_features[i];
+ j++;
+ }
+ num_msr_based_features = j;
}
static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
* handle watchpoints yet, those would be handled in
* the emulate_ops.
*/
- if (kvm_vcpu_check_breakpoint(vcpu, &r))
+ if (!(emulation_type & EMULTYPE_SKIP) &&
+ kvm_vcpu_check_breakpoint(vcpu, &r))
return r;
ctxt->interruptibility = 0;
__this_cpu_write(cpu_tsc_khz, khz);
}
+#ifdef CONFIG_X86_64
+static void kvm_hyperv_tsc_notifier(void)
+{
+ struct kvm *kvm;
+ struct kvm_vcpu *vcpu;
+ int cpu;
+
+ spin_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ kvm_make_mclock_inprogress_request(kvm);
+
+ hyperv_stop_tsc_emulation();
+
+ /* TSC frequency always matches when on Hyper-V */
+ for_each_present_cpu(cpu)
+ per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+ kvm_max_guest_tsc_khz = tsc_khz;
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ struct kvm_arch *ka = &kvm->arch;
+
+ spin_lock(&ka->pvclock_gtod_sync_lock);
+
+ pvclock_update_vm_gtod_copy(kvm);
+
+ kvm_for_each_vcpu(cpu, vcpu, kvm)
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+
+ kvm_for_each_vcpu(cpu, vcpu, kvm)
+ kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
+
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+ }
+ spin_unlock(&kvm_lock);
+}
+#endif
+
static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
update_pvclock_gtod(tk);
/* disable master clock if host does not trust, or does not
- * use, TSC clocksource
+ * use, TSC based clocksource.
*/
- if (gtod->clock.vclock_mode != VCLOCK_TSC &&
+ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
atomic_read(&kvm_guest_has_master_clock) != 0)
queue_work(system_long_wq, &pvclock_gtod_work);
kvm_lapic_init();
#ifdef CONFIG_X86_64
pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
+
+ if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
+ set_hv_tscchange_cb(kvm_hyperv_tsc_notifier);
#endif
return 0;
void kvm_arch_exit(void)
{
+#ifdef CONFIG_X86_64
+ if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
+ clear_hv_tscchange_cb();
+#endif
kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
kvm_x86_ops->queue_exception(vcpu);
} else if (vcpu->arch.smi_pending && !is_smm(vcpu) && kvm_x86_ops->smi_allowed(vcpu)) {
vcpu->arch.smi_pending = false;
+ ++vcpu->arch.smi_count;
enter_smm(vcpu);
} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
--vcpu->arch.nmi_pending;
if (irqchip_split(vcpu->kvm))
kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
else {
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
+ if (vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
}
kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
}
-static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
-{
- ++vcpu->stat.tlb_flush;
- kvm_x86_ops->tlb_flush(vcpu);
-}
-
void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
unsigned long start, unsigned long end)
{
if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
kvm_mmu_sync_roots(vcpu);
if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
- kvm_vcpu_flush_tlb(vcpu);
+ kvm_vcpu_flush_tlb(vcpu, true);
if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
* This handles the case where a posted interrupt was
* notified with kvm_vcpu_kick.
*/
- if (kvm_lapic_enabled(vcpu)) {
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
- kvm_x86_ops->sync_pir_to_irr(vcpu);
- }
+ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
+ kvm_x86_ops->sync_pir_to_irr(vcpu);
if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu)
|| need_resched() || signal_pending(current)) {
}
trace_kvm_entry(vcpu->vcpu_id);
- wait_lapic_expire(vcpu);
+ if (lapic_timer_advance_ns)
+ wait_lapic_expire(vcpu);
guest_enter_irqoff();
if (unlikely(vcpu->arch.switch_db_regs)) {
return 0;
}
-
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
+ vcpu_load(vcpu);
kvm_sigset_activate(vcpu);
-
kvm_load_guest_fpu(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
goto out;
}
+ if (vcpu->run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) {
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (vcpu->run->kvm_dirty_regs) {
+ r = sync_regs(vcpu);
+ if (r != 0)
+ goto out;
+ }
+
/* re-sync apic's tpr */
if (!lapic_in_kernel(vcpu)) {
if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) {
out:
kvm_put_guest_fpu(vcpu);
+ if (vcpu->run->kvm_valid_regs)
+ store_regs(vcpu);
post_kvm_run_save(vcpu);
kvm_sigset_deactivate(vcpu);
+ vcpu_put(vcpu);
return r;
}
-int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
if (vcpu->arch.emulate_regs_need_sync_to_vcpu) {
/*
regs->rip = kvm_rip_read(vcpu);
regs->rflags = kvm_get_rflags(vcpu);
+}
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_load(vcpu);
+ __get_regs(vcpu, regs);
+ vcpu_put(vcpu);
return 0;
}
-int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
vcpu->arch.emulate_regs_need_sync_from_vcpu = true;
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
vcpu->arch.exception.pending = false;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_load(vcpu);
+ __set_regs(vcpu, regs);
+ vcpu_put(vcpu);
return 0;
}
}
EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
- struct kvm_sregs *sregs)
+static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct desc_ptr dt;
if (vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft)
set_bit(vcpu->arch.interrupt.nr,
(unsigned long *)sregs->interrupt_bitmap);
+}
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ vcpu_load(vcpu);
+ __get_sregs(vcpu, sregs);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ vcpu_load(vcpu);
+
kvm_apic_accept_events(vcpu);
if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
vcpu->arch.pv.pv_unhalted)
else
mp_state->mp_state = vcpu->arch.mp_state;
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ int ret = -EINVAL;
+
+ vcpu_load(vcpu);
+
if (!lapic_in_kernel(vcpu) &&
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
- return -EINVAL;
+ goto out;
/* INITs are latched while in SMM */
if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
(mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
- return -EINVAL;
+ goto out;
if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
} else
vcpu->arch.mp_state = mp_state->mp_state;
kvm_make_request(KVM_REQ_EVENT, vcpu);
- return 0;
+
+ ret = 0;
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
return 0;
}
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
- struct kvm_sregs *sregs)
+static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct msr_data apic_base_msr;
int mmu_reset_needed = 0;
int pending_vec, max_bits, idx;
struct desc_ptr dt;
+ int ret = -EINVAL;
if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
(sregs->cr4 & X86_CR4_OSXSAVE))
- return -EINVAL;
+ goto out;
if (kvm_valid_sregs(vcpu, sregs))
- return -EINVAL;
+ goto out;
apic_base_msr.data = sregs->apic_base;
apic_base_msr.host_initiated = true;
if (kvm_set_apic_base(vcpu, &apic_base_msr))
- return -EINVAL;
+ goto out;
dt.size = sregs->idt.limit;
dt.address = sregs->idt.base;
kvm_make_request(KVM_REQ_EVENT, vcpu);
- return 0;
+ ret = 0;
+out:
+ return ret;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ int ret;
+
+ vcpu_load(vcpu);
+ ret = __set_sregs(vcpu, sregs);
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
unsigned long rflags;
int i, r;
+ vcpu_load(vcpu);
+
if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
r = -EBUSY;
if (vcpu->arch.exception.pending)
r = 0;
out:
-
+ vcpu_put(vcpu);
return r;
}
gpa_t gpa;
int idx;
+ vcpu_load(vcpu);
+
idx = srcu_read_lock(&vcpu->kvm->srcu);
gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
tr->writeable = 1;
tr->usermode = 0;
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxregs_state *fxsave =
- &vcpu->arch.guest_fpu.state.fxsave;
+ struct fxregs_state *fxsave;
+
+ vcpu_load(vcpu);
+ fxsave = &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->fsw = fxsave->swd;
fpu->last_dp = fxsave->rdp;
memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxregs_state *fxsave =
- &vcpu->arch.guest_fpu.state.fxsave;
+ struct fxregs_state *fxsave;
+
+ vcpu_load(vcpu);
+
+ fxsave = &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
fxsave->rdp = fpu->last_dp;
memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);
+ vcpu_put(vcpu);
+ return 0;
+}
+
+static void store_regs(struct kvm_vcpu *vcpu)
+{
+ BUILD_BUG_ON(sizeof(struct kvm_sync_regs) > SYNC_REGS_SIZE_BYTES);
+
+ if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_REGS)
+ __get_regs(vcpu, &vcpu->run->s.regs.regs);
+
+ if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_SREGS)
+ __get_sregs(vcpu, &vcpu->run->s.regs.sregs);
+
+ if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_EVENTS)
+ kvm_vcpu_ioctl_x86_get_vcpu_events(
+ vcpu, &vcpu->run->s.regs.events);
+}
+
+static int sync_regs(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)
+ return -EINVAL;
+
+ if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) {
+ __set_regs(vcpu, &vcpu->run->s.regs.regs);
+ vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS;
+ }
+ if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) {
+ if (__set_sregs(vcpu, &vcpu->run->s.regs.sregs))
+ return -EINVAL;
+ vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS;
+ }
+ if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) {
+ if (kvm_vcpu_ioctl_x86_set_vcpu_events(
+ vcpu, &vcpu->run->s.regs.events))
+ return -EINVAL;
+ vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS;
+ }
+
return 0;
}
{
struct kvm_vcpu *vcpu;
- if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+ if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
printk_once(KERN_WARNING
"kvm: SMP vm created on host with unstable TSC; "
"guest TSC will not be reliable\n");
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
- int r;
-
kvm_vcpu_mtrr_init(vcpu);
- r = vcpu_load(vcpu);
- if (r)
- return r;
+ vcpu_load(vcpu);
kvm_vcpu_reset(vcpu, false);
kvm_mmu_setup(vcpu);
vcpu_put(vcpu);
- return r;
+ return 0;
}
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
kvm_hv_vcpu_postcreate(vcpu);
- if (vcpu_load(vcpu))
+ if (mutex_lock_killable(&vcpu->mutex))
return;
+ vcpu_load(vcpu);
msr.data = 0x0;
msr.index = MSR_IA32_TSC;
msr.host_initiated = true;
kvm_write_tsc(vcpu, &msr);
vcpu_put(vcpu);
+ mutex_unlock(&vcpu->mutex);
if (!kvmclock_periodic_sync)
return;
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- int r;
vcpu->arch.apf.msr_val = 0;
- r = vcpu_load(vcpu);
- BUG_ON(r);
+ vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
+ kvm_lapic_reset(vcpu, init_event);
+
vcpu->arch.hflags = 0;
vcpu->arch.smi_pending = 0;
+ vcpu->arch.smi_count = 0;
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
return ret;
local_tsc = rdtsc();
- stable = !check_tsc_unstable();
+ stable = !kvm_check_tsc_unstable();
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!stable && vcpu->cpu == smp_processor_id())
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
- mutex_init(&kvm->arch.hyperv.hv_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+ kvm_hv_init_vm(kvm);
kvm_page_track_init(kvm);
kvm_mmu_init_vm(kvm);
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
- int r;
- r = vcpu_load(vcpu);
- BUG_ON(r);
+ vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
}
return r;
}
- if (!size) {
- r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
- WARN_ON(r < 0);
- }
+ if (!size)
+ vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
return 0;
}
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kvm_mmu_uninit_vm(kvm);
kvm_page_track_cleanup(kvm);
+ kvm_hv_destroy_vm(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
projects / linux.git / blobdiff