#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
#include <asm/microcode.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include "trace.h"
#include "pmu.h"
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+static bool __read_mostly nosmt;
+module_param(nosmt, bool, S_IRUGO);
+
static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
extern const ulong vmx_return;
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+
+/* These MUST be in sync with vmentry_l1d_param order. */
+enum vmx_l1d_flush_state {
+ VMENTER_L1D_FLUSH_NEVER,
+ VMENTER_L1D_FLUSH_COND,
+ VMENTER_L1D_FLUSH_ALWAYS,
+};
+
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
+
+static const struct {
+ const char *option;
+ enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+ {"never", VMENTER_L1D_FLUSH_NEVER},
+ {"cond", VMENTER_L1D_FLUSH_COND},
+ {"always", VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+ unsigned int i;
+
+ if (!s)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+ if (!strcmp(s, vmentry_l1d_param[i].option)) {
+ vmentry_l1d_flush = vmentry_l1d_param[i].cmd;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+ return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+ .set = vmentry_l1d_flush_set,
+ .get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO);
+
#define NR_AUTOLOAD_MSRS 8
struct vmcs {
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
/* The STIBP bit doesn't fault even if it's not advertised */
- if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+ if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
return 1;
vmx->spec_ctrl = data;
break;
case MSR_IA32_PRED_CMD:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
if (!is_guest_mode(vcpu) &&
!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
trace_kvm_fast_mmio(gpa);
- return kvm_skip_emulated_instruction(vcpu);
+ /*
+ * Doing kvm_skip_emulated_instruction() depends on undefined
+ * behavior: Intel's manual doesn't mandate
+ * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
+ * occurs and while on real hardware it was observed to be set,
+ * other hypervisors (namely Hyper-V) don't set it, we end up
+ * advancing IP with some random value. Disable fast mmio when
+ * running nested and keep it for real hardware in hope that
+ * VM_EXIT_INSTRUCTION_LEN will always be set correctly.
+ */
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ return kvm_skip_emulated_instruction(vcpu);
+ else
+ return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
+ NULL, 0) == EMULATE_DONE;
}
ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
}
}
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
+{
+ int size = PAGE_SIZE << L1D_CACHE_ORDER;
+ bool always;
+
+ /*
+ * If the mitigation mode is 'flush always', keep the flush bit
+ * set, otherwise clear it. It gets set again either from
+ * vcpu_run() or from one of the unsafe VMEXIT handlers.
+ */
+ always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+ vcpu->arch.l1tf_flush_l1d = always;
+
+ vcpu->stat.l1d_flush++;
+
+ if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+ wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ return;
+ }
+
+ asm volatile(
+ /* First ensure the pages are in the TLB */
+ "xorl %%eax, %%eax\n"
+ ".Lpopulate_tlb:\n\t"
+ "movzbl (%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+ "addl $4096, %%eax\n\t"
+ "cmpl %%eax, %[size]\n\t"
+ "jne .Lpopulate_tlb\n\t"
+ "xorl %%eax, %%eax\n\t"
+ "cpuid\n\t"
+ /* Now fill the cache */
+ "xorl %%eax, %%eax\n"
+ ".Lfill_cache:\n"
+ "movzbl (%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+ "addl $64, %%eax\n\t"
+ "cmpl %%eax, %[size]\n\t"
+ "jne .Lfill_cache\n\t"
+ "lfence\n"
+ :: [empty_zp] "r" (vmx_l1d_flush_pages),
+ [size] "r" (size)
+ : "eax", "ebx", "ecx", "edx");
+}
+
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
+ vcpu->arch.l1tf_flush_l1d = true;
}
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
{
- return enable_unrestricted_guest || emulate_invalid_guest_state;
+ switch (index) {
+ case MSR_IA32_SMBASE:
+ /*
+ * We cannot do SMM unless we can run the guest in big
+ * real mode.
+ */
+ return enable_unrestricted_guest || emulate_invalid_guest_state;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ /* This is AMD only. */
+ return false;
+ default:
+ return true;
+ }
}
static bool vmx_mpx_supported(void)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- x86_spec_ctrl_set_guest(vmx->spec_ctrl);
+ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
vmx->__launched = vmx->loaded_vmcs->launched;
+
+ if (static_branch_unlikely(&vmx_l1d_should_flush)) {
+ if (vcpu->arch.l1tf_flush_l1d)
+ vmx_l1d_flush(vcpu);
+ }
+
asm(
/* Store host registers */
"push %%" _ASM_DX "; push %%" _ASM_BP ";"
if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- x86_spec_ctrl_restore_host(vmx->spec_ctrl);
+ x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
return ERR_PTR(err);
}
+#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+
+static int vmx_vm_init(struct kvm *kvm)
+{
+ if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
+ if (nosmt) {
+ pr_err(L1TF_MSG);
+ return -EOPNOTSUPP;
+ }
+ pr_warn(L1TF_MSG);
+ }
+ return 0;
+}
+
static void __init vmx_check_processor_compat(void *rtn)
{
struct vmcs_config vmcs_conf;
if (ret)
return ret;
+ /* Hide L1D cache contents from the nested guest. */
+ vmx->vcpu.arch.l1tf_flush_l1d = true;
+
if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
return kvm_vcpu_halt(vcpu);
.hardware_enable = hardware_enable,
.hardware_disable = hardware_disable,
.cpu_has_accelerated_tpr = report_flexpriority,
- .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+ .has_emulated_msr = vmx_has_emulated_msr,
+
+ .vm_init = vmx_vm_init,
.vcpu_create = vmx_create_vcpu,
.vcpu_free = vmx_free_vcpu,
.enable_smi_window = enable_smi_window,
};
+static int __init vmx_setup_l1d_flush(void)
+{
+ struct page *page;
+
+ if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
+ !boot_cpu_has_bug(X86_BUG_L1TF))
+ return 0;
+
+ if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+ if (!page)
+ return -ENOMEM;
+ vmx_l1d_flush_pages = page_address(page);
+ }
+
+ static_branch_enable(&vmx_l1d_should_flush);
+ return 0;
+}
+
+static void vmx_free_l1d_flush_pages(void)
+{
+ if (vmx_l1d_flush_pages) {
+ free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+ vmx_l1d_flush_pages = NULL;
+ }
+}
+
static int __init vmx_init(void)
{
- int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
- __alignof__(struct vcpu_vmx), THIS_MODULE);
+ int r;
+
+ r = vmx_setup_l1d_flush();
if (r)
return r;
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
+ if (r) {
+ vmx_free_l1d_flush_pages();
+ return r;
+ }
+
#ifdef CONFIG_KEXEC_CORE
rcu_assign_pointer(crash_vmclear_loaded_vmcss,
crash_vmclear_local_loaded_vmcss);
#endif
kvm_exit();
+
+ vmx_free_l1d_flush_pages();
}
module_init(vmx_init)