static bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
static bool __read_mostly kvmclock_periodic_sync = true;
{ "irq_injections", VCPU_STAT(irq_injections) },
{ "nmi_injections", VCPU_STAT(nmi_injections) },
{ "req_event", VCPU_STAT(req_event) },
+ { "l1d_flush", VCPU_STAT(l1d_flush) },
{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
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;
}
if (is_long_mode(vcpu) &&
- (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 62)))
+ (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
return 1;
else if (is_pae(vcpu) && is_paging(vcpu) &&
!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
#endif
MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+ MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
};
static unsigned num_msrs_to_save;
MSR_IA32_SMBASE,
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
+ MSR_AMD64_VIRT_SPEC_CTRL,
};
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_F10H_DECFG,
+ MSR_IA32_UCODE_REV,
+ MSR_IA32_ARCH_CAPABILITIES,
+};
+
+static unsigned int num_msr_based_features;
+
+u64 kvm_get_arch_capabilities(void)
+{
+ u64 data;
+
+ rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+ /*
+ * If we're doing cache flushes (either "always" or "cond")
+ * we will do one whenever the guest does a vmlaunch/vmresume.
+ * If an outer hypervisor is doing the cache flush for us
+ * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
+ * capability to the guest too, and if EPT is disabled we're not
+ * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will
+ * require a nested hypervisor to do a flush of its own.
+ */
+ if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
+ data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
+static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+ switch (msr->index) {
+ case MSR_IA32_ARCH_CAPABILITIES:
+ msr->data = kvm_get_arch_capabilities();
+ break;
+ case MSR_IA32_UCODE_REV:
+ rdmsrl_safe(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)
static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
{
- u64 curr_offset = vcpu->arch.tsc_offset;
+ u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
- return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+ u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+ return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
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_IA32_TSC:
+ kvm_write_tsc(vcpu, msr_info);
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
msr_info->data = 0;
break;
case MSR_IA32_UCODE_REV:
- msr_info->data = 0x100000000ULL;
+ msr_info->data = vcpu->arch.microcode_version;
+ break;
+ case MSR_IA32_TSC:
+ msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
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_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_ADJUST_CLOCK:
* fringe case that is not enabled except via specific settings
* of the module parameters.
*/
- r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+ r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
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;
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,
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;
mutex_unlock(&kvm->lock);
break;
case KVM_XEN_HVM_CONFIG: {
+ struct kvm_xen_hvm_config xhc;
r = -EFAULT;
- if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
- sizeof(struct kvm_xen_hvm_config)))
+ if (copy_from_user(&xhc, argp, sizeof(xhc)))
goto out;
r = -EINVAL;
- if (kvm->arch.xen_hvm_config.flags)
+ if (xhc.flags)
goto out;
+ memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc));
r = 0;
break;
}
num_msrs_to_save = j;
for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
- switch (emulated_msrs[i]) {
- case MSR_IA32_SMBASE:
- if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
- continue;
- break;
- default:
- break;
- }
+ if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+ continue;
if (j < i)
emulated_msrs[j] = emulated_msrs[i];
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,
return X86EMUL_CONTINUE;
}
-int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
+int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ /*
+ * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+ * is returned, but our callers are not ready for that and they blindly
+ * call kvm_inject_page_fault. Ensure that they at least do not leak
+ * uninitialized kernel stack memory into cr2 and error code.
+ */
+ memset(exception, 0, sizeof(*exception));
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
exception);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_virt);
-static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt,
- gva_t addr, void *val, unsigned int bytes,
- struct x86_exception *exception)
+static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
+ gva_t addr, void *val, unsigned int bytes,
+ struct x86_exception *exception, bool system)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
+ u32 access = 0;
+
+ if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+ access |= PFERR_USER_MASK;
+
+ return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
}
static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
}
-int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
- gva_t addr, void *val,
- unsigned int bytes,
- struct x86_exception *exception)
+static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
+ struct kvm_vcpu *vcpu, u32 access,
+ struct x86_exception *exception)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
- PFERR_WRITE_MASK,
+ access,
exception);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
out:
return r;
}
+
+static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val,
+ unsigned int bytes, struct x86_exception *exception,
+ bool system)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+ u32 access = PFERR_WRITE_MASK;
+
+ if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+ access |= PFERR_USER_MASK;
+
+ return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+ access, exception);
+}
+
+int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
+ unsigned int bytes, struct x86_exception *exception)
+{
+ /* kvm_write_guest_virt_system can pull in tons of pages. */
+ vcpu->arch.l1tf_flush_l1d = true;
+
+ return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+ PFERR_WRITE_MASK, exception);
+}
EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
static const struct x86_emulate_ops emulate_ops = {
.read_gpr = emulator_read_gpr,
.write_gpr = emulator_write_gpr,
- .read_std = kvm_read_guest_virt_system,
- .write_std = kvm_write_guest_virt_system,
+ .read_std = emulator_read_std,
+ .write_std = emulator_write_std,
.read_phys = kvm_read_guest_phys_system,
.fetch = kvm_fetch_guest_virt,
.read_emulated = emulator_read_emulated,
bool writeback = true;
bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
+ vcpu->arch.l1tf_flush_l1d = true;
+
/*
* Clear write_fault_to_shadow_pgtable here to ensure it is
* never reused.
* 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;
goto out;
}
if (ops->disabled_by_bios()) {
- printk(KERN_ERR "kvm: disabled by bios\n");
+ printk(KERN_WARNING "kvm: disabled by bios\n");
r = -EOPNOTSUPP;
goto out;
}
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
- int op_64_bit, r;
+ int op_64_bit;
- r = kvm_skip_emulated_instruction(vcpu);
-
- if (kvm_hv_hypercall_enabled(vcpu->kvm))
- return kvm_hv_hypercall(vcpu);
+ if (kvm_hv_hypercall_enabled(vcpu->kvm)) {
+ if (!kvm_hv_hypercall(vcpu))
+ return 0;
+ goto out;
+ }
nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
if (kvm_x86_ops->get_cpl(vcpu) != 0) {
ret = -KVM_EPERM;
- goto out;
+ goto out_error;
}
switch (nr) {
ret = -KVM_ENOSYS;
break;
}
-out:
+out_error:
if (!op_64_bit)
ret = (u32)ret;
kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
+out:
++vcpu->stat.hypercalls;
- return r;
+ return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
else {
if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
- kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
+ if (ioapic_in_kernel(vcpu->kvm))
+ kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
}
bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors,
vcpu_to_synic(vcpu)->vec_bitmap, 256);
struct kvm *kvm = vcpu->kvm;
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+ vcpu->arch.l1tf_flush_l1d = true;
for (;;) {
if (kvm_vcpu_running(vcpu)) {
int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
- if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+ if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
/*
* When EFER.LME and CR0.PG are set, the processor is in
* 64-bit mode (though maybe in a 32-bit code segment).
* CR4.PAE and EFER.LMA must be set.
*/
- if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+ if (!(sregs->cr4 & X86_CR4_PAE)
|| !(sregs->efer & EFER_LMA))
return -EINVAL;
} else {
{
struct msr_data apic_base_msr;
int mmu_reset_needed = 0;
+ int cpuid_update_needed = 0;
int pending_vec, max_bits, idx;
struct desc_ptr dt;
vcpu->arch.cr0 = sregs->cr0;
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+ cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+ (X86_CR4_OSXSAVE | X86_CR4_PKE));
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
- if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+ if (cpuid_update_needed)
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
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;
void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
+ vcpu->arch.l1tf_flush_l1d = true;
kvm_x86_ops->sched_in(vcpu, cpu);
}
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;
}
projects / mirror_ubuntu-bionic-kernel.git / blobdiff