#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/microcode.h>
+#include <asm/spec-ctrl.h>
#include "trace.h"
#include "pmu.h"
extern const ulong vmx_return;
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
+static DEFINE_MUTEX(vmx_l1d_flush_mutex);
+
+/* Storage for pre module init parameter parsing */
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
+
+static const struct {
+ const char *option;
+ bool for_parse;
+} vmentry_l1d_param[] = {
+ [VMENTER_L1D_FLUSH_AUTO] = {"auto", true},
+ [VMENTER_L1D_FLUSH_NEVER] = {"never", true},
+ [VMENTER_L1D_FLUSH_COND] = {"cond", true},
+ [VMENTER_L1D_FLUSH_ALWAYS] = {"always", true},
+ [VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false},
+ [VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false},
+};
+
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
+{
+ struct page *page;
+ unsigned int i;
+
+ if (!enable_ept) {
+ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+ return 0;
+ }
+
+ if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+ u64 msr;
+
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+ if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+ return 0;
+ }
+ }
+
+ /* If set to auto use the default l1tf mitigation method */
+ if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+ switch (l1tf_mitigation) {
+ case L1TF_MITIGATION_OFF:
+ l1tf = VMENTER_L1D_FLUSH_NEVER;
+ break;
+ case L1TF_MITIGATION_FLUSH_NOWARN:
+ case L1TF_MITIGATION_FLUSH:
+ case L1TF_MITIGATION_FLUSH_NOSMT:
+ l1tf = VMENTER_L1D_FLUSH_COND;
+ break;
+ case L1TF_MITIGATION_FULL:
+ case L1TF_MITIGATION_FULL_FORCE:
+ l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+ break;
+ }
+ } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+ l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+ }
+
+ if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
+ !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);
+
+ /*
+ * Initialize each page with a different pattern in
+ * order to protect against KSM in the nested
+ * virtualization case.
+ */
+ for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
+ memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
+ PAGE_SIZE);
+ }
+ }
+
+ l1tf_vmx_mitigation = l1tf;
+
+ if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+ static_branch_enable(&vmx_l1d_should_flush);
+ else
+ static_branch_disable(&vmx_l1d_should_flush);
+
+ if (l1tf == VMENTER_L1D_FLUSH_COND)
+ static_branch_enable(&vmx_l1d_flush_cond);
+ else
+ static_branch_disable(&vmx_l1d_flush_cond);
+ return 0;
+}
+
+static int vmentry_l1d_flush_parse(const char *s)
+{
+ unsigned int i;
+
+ if (s) {
+ for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+ if (vmentry_l1d_param[i].for_parse &&
+ sysfs_streq(s, vmentry_l1d_param[i].option))
+ return i;
+ }
+ }
+ return -EINVAL;
+}
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+ int l1tf, ret;
+
+ l1tf = vmentry_l1d_flush_parse(s);
+ if (l1tf < 0)
+ return l1tf;
+
+ if (!boot_cpu_has(X86_BUG_L1TF))
+ return 0;
+
+ /*
+ * Has vmx_init() run already? If not then this is the pre init
+ * parameter parsing. In that case just store the value and let
+ * vmx_init() do the proper setup after enable_ept has been
+ * established.
+ */
+ if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
+ vmentry_l1d_flush_param = l1tf;
+ return 0;
+ }
+
+ mutex_lock(&vmx_l1d_flush_mutex);
+ ret = vmx_setup_l1d_flush(l1tf);
+ mutex_unlock(&vmx_l1d_flush_mutex);
+ return ret;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+ if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
+ return sprintf(s, "???\n");
+
+ return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].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, NULL, 0644);
+
#define NR_AUTOLOAD_MSRS 8
struct vmcs {
(unsigned long *)&pi_desc->control);
}
+struct vmx_msrs {
+ unsigned int nr;
+ struct vmx_msr_entry val[NR_AUTOLOAD_MSRS];
+};
+
struct vcpu_vmx {
struct kvm_vcpu vcpu;
unsigned long host_rsp;
struct loaded_vmcs *loaded_vmcs;
bool __launched; /* temporary, used in vmx_vcpu_run */
struct msr_autoload {
- unsigned nr;
- struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
- struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+ struct vmx_msrs guest;
+ struct vmx_msrs host;
} msr_autoload;
struct {
int loaded;
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+ return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+ == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
vm_exit_controls_clearbit(vmx, exit);
}
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+ unsigned int i;
+
+ for (i = 0; i < m->nr; ++i) {
+ if (m->val[i].index == msr)
+ return i;
+ }
+ return -ENOENT;
+}
+
static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
- unsigned i;
+ int i;
struct msr_autoload *m = &vmx->msr_autoload;
switch (msr) {
}
break;
}
+ i = find_msr(&m->guest, msr);
+ if (i < 0)
+ goto skip_guest;
+ --m->guest.nr;
+ m->guest.val[i] = m->guest.val[m->guest.nr];
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
- for (i = 0; i < m->nr; ++i)
- if (m->guest[i].index == msr)
- break;
-
- if (i == m->nr)
+skip_guest:
+ i = find_msr(&m->host, msr);
+ if (i < 0)
return;
- --m->nr;
- m->guest[i] = m->guest[m->nr];
- m->host[i] = m->host[m->nr];
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+
+ --m->host.nr;
+ m->host.val[i] = m->host.val[m->host.nr];
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
}
static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
}
static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
- u64 guest_val, u64 host_val)
+ u64 guest_val, u64 host_val, bool entry_only)
{
- unsigned i;
+ int i, j = 0;
struct msr_autoload *m = &vmx->msr_autoload;
switch (msr) {
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
- for (i = 0; i < m->nr; ++i)
- if (m->guest[i].index == msr)
- break;
+ i = find_msr(&m->guest, msr);
+ if (!entry_only)
+ j = find_msr(&m->host, msr);
- if (i == NR_AUTOLOAD_MSRS) {
+ if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
printk_once(KERN_WARNING "Not enough msr switch entries. "
"Can't add msr %x\n", msr);
return;
- } else if (i == m->nr) {
- ++m->nr;
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}
+ if (i < 0) {
+ i = m->guest.nr++;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+ }
+ m->guest.val[i].index = msr;
+ m->guest.val[i].value = guest_val;
- m->guest[i].index = msr;
- m->guest[i].value = guest_val;
- m->host[i].index = msr;
- m->host[i].value = host_val;
+ if (entry_only)
+ return;
+
+ if (j < 0) {
+ j = m->host.nr++;
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+ }
+ m->host.val[j].index = msr;
+ m->host.val[j].value = host_val;
}
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
- guest_efer, host_efer);
+ guest_efer, host_efer, false);
return false;
} else {
guest_efer &= ~ignore_bits;
return;
}
+ WARN_ON_ONCE(vmx->emulation_required);
+
if (kvm_exception_is_soft(nr)) {
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmx->vcpu.arch.event_exit_inst_len);
vmx_update_msr_bitmap(&vmx->vcpu);
}
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
{
- u64 host_tsc, tsc_offset;
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- host_tsc = rdtsc();
- tsc_offset = vmcs_read64(TSC_OFFSET);
- return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+ if (is_guest_mode(vcpu) &&
+ (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+ return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+ return vcpu->arch.tsc_offset;
}
/*
return !(val & ~valid_bits);
}
+static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
+{
+ return 1;
+}
+
/*
* Reads an msr value (of 'msr_index') into 'pdata'.
* Returns 0 on success, non-0 otherwise.
#endif
case MSR_EFER:
return kvm_get_msr_common(vcpu, msr_info);
- case MSR_IA32_TSC:
- msr_info->data = guest_read_tsc(vcpu);
- 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;
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
- case MSR_IA32_TSC:
- kvm_write_tsc(vcpu, msr_info);
- 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;
vcpu->arch.ia32_xss = data;
if (vcpu->arch.ia32_xss != host_xss)
add_atomic_switch_msr(vmx, MSR_IA32_XSS,
- vcpu->arch.ia32_xss, host_xss);
+ vcpu->arch.ia32_xss, host_xss, false);
else
clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
break;
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
}
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
- if (enable_ept)
- vmx_flush_tlb(vcpu);
-}
-
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
- vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
++vmx->nmsrs;
}
- if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
+ vmx->arch_capabilities = kvm_get_arch_capabilities();
vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
vmx->rmode.vm86_active = 0;
vmx->spec_ctrl = 0;
+ vcpu->arch.microcode_version = 0x100000000ULL;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(vcpu, 0);
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
vcpu->arch.dr6 &= ~15;
vcpu->arch.dr6 |= dr6 | DR6_RTM;
- if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+ if (is_icebp(intr_info))
skip_emulated_instruction(vcpu);
kvm_queue_exception(vcpu, DB_VECTOR);
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);
goto out;
}
- if (err != EMULATE_DONE) {
- vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
- vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
- vcpu->run->internal.ndata = 0;
- return 0;
- }
+ if (err != EMULATE_DONE)
+ goto emulation_error;
+
+ if (vmx->emulation_required && !vmx->rmode.vm86_active &&
+ vcpu->arch.exception.pending)
+ goto emulation_error;
if (vcpu->arch.halt_request) {
vcpu->arch.halt_request = 0;
out:
return ret;
+
+emulation_error:
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
+ return 0;
}
static int __grow_ple_window(int val)
vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
- sizeof(*vmpointer), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
return 1;
}
+ /* CPL=0 must be checked manually. */
+ if (vmx_get_cpl(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
if (vmx->nested.vmxon) {
nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
return kvm_skip_emulated_instruction(vcpu);
*/
static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
{
+ if (vmx_get_cpl(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
if (!to_vmx(vcpu)->nested.vmxon) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 0;
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
+ hrtimer_cancel(&vmx->nested.preemption_timer);
vmx->nested.vmxon = false;
vmx->nested.smm.vmxon = false;
free_vpid(vmx->nested.vpid02);
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, true, &gva))
return 1;
- /* _system ok, as hardware has verified cpl=0 */
- kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
- &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
+ /* _system ok, nested_vmx_check_permission has verified cpl=0 */
+ kvm_write_guest_virt_system(vcpu, gva, &field_value,
+ (is_long_mode(vcpu) ? 8 : 4), NULL);
}
nested_vmx_succeed(vcpu);
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
- &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &field_value,
+ (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, true, &vmcs_gva))
return 1;
- /* ok to use *_system, as hardware has verified cpl=0 */
- if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
- (void *)&to_vmx(vcpu)->nested.current_vmptr,
- sizeof(u64), &e)) {
+ /* *_system ok, nested_vmx_check_permission has verified cpl=0 */
+ if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
+ (void *)&to_vmx(vcpu)->nested.current_vmptr,
+ sizeof(u64), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
- sizeof(operand), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
- sizeof(operand), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
}
}
+/*
+ * 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;
+
+ /*
+ * This code is only executed when the the flush mode is 'cond' or
+ * 'always'
+ */
+ if (static_branch_likely(&vmx_l1d_flush_cond)) {
+ bool flush_l1d;
+
+ /*
+ * Clear the per-vcpu flush bit, it gets set again
+ * either from vcpu_run() or from one of the unsafe
+ * VMEXIT handlers.
+ */
+ flush_l1d = vcpu->arch.l1tf_flush_l1d;
+ vcpu->arch.l1tf_flush_l1d = false;
+
+ /*
+ * Clear the per-cpu flush bit, it gets set again from
+ * the interrupt handlers.
+ */
+ flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
+ kvm_clear_cpu_l1tf_flush_l1d();
+
+ if (!flush_l1d)
+ return;
+ }
+
+ 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 (%[flush_pages], %%" _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 (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+ "addl $64, %%eax\n\t"
+ "cmpl %%eax, %[size]\n\t"
+ "jne .Lfill_cache\n\t"
+ "lfence\n"
+ :: [flush_pages] "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);
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu);
}
}
}
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)
clear_atomic_switch_msr(vmx, msrs[i].msr);
else
add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
- msrs[i].host);
+ msrs[i].host, false);
}
static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- if (vmx->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, 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))
+ vmx_l1d_flush(vcpu);
+
asm(
/* Store host registers */
"push %%" _ASM_DX "; push %%" _ASM_BP ";"
* If the L02 MSR bitmap does not intercept the MSR, then we need to
* save it.
*/
- if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
- rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+ if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+ vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- if (vmx->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ 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 "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+
+static int vmx_vm_init(struct kvm *kvm)
+{
+ if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+ switch (l1tf_mitigation) {
+ case L1TF_MITIGATION_OFF:
+ case L1TF_MITIGATION_FLUSH_NOWARN:
+ /* 'I explicitly don't care' is set */
+ break;
+ case L1TF_MITIGATION_FLUSH:
+ case L1TF_MITIGATION_FLUSH_NOSMT:
+ case L1TF_MITIGATION_FULL:
+ /*
+ * Warn upon starting the first VM in a potentially
+ * insecure environment.
+ */
+ if (cpu_smt_control == CPU_SMT_ENABLED)
+ pr_warn_once(L1TF_MSG_SMT);
+ if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+ pr_warn_once(L1TF_MSG_L1D);
+ break;
+ case L1TF_MITIGATION_FULL_FORCE:
+ /* Flush is enforced */
+ break;
+ }
+ }
+ return 0;
+}
+
static void __init vmx_check_processor_compat(void *rtn)
{
struct vmcs_config vmcs_conf;
kunmap(vmx->nested.pi_desc_page);
kvm_release_page_dirty(vmx->nested.pi_desc_page);
vmx->nested.pi_desc_page = NULL;
+ vmx->nested.pi_desc = NULL;
+ vmcs_write64(POSTED_INTR_DESC_ADDR, -1ull);
}
page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->posted_intr_desc_addr);
if (is_error_page(page))
return true;
}
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+ !page_address_valid(vcpu, vmcs12->apic_access_addr))
+ return -EINVAL;
+ else
+ return 0;
+}
+
static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
* Set the MSR load/store lists to match L0's settings.
*/
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
/*
* HOST_RSP is normally set correctly in vmx_vcpu_run() just before
vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)
vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
- vmcs_write64(TSC_OFFSET,
- vcpu->arch.tsc_offset + vmcs12->tsc_offset);
- else
- vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+ vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
}
} else if (nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu);
}
/*
if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
u32 msr_entry_idx;
u32 exit_qual;
+ int r;
enter_guest_mode(vcpu);
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
vmx_segment_cache_clear(vmx);
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+ r = EXIT_REASON_INVALID_STATE;
+ if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+ goto fail;
nested_get_vmcs12_pages(vcpu, vmcs12);
+ r = EXIT_REASON_MSR_LOAD_FAIL;
msr_entry_idx = nested_vmx_load_msr(vcpu,
vmcs12->vm_entry_msr_load_addr,
vmcs12->vm_entry_msr_load_count);
- if (msr_entry_idx) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
- return 1;
- }
+ if (msr_entry_idx)
+ goto fail;
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
* the success flag) when L2 exits (see nested_vmx_vmexit()).
*/
return 0;
+
+fail:
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+ leave_guest_mode(vcpu);
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+ return 1;
}
/*
if (ret)
return ret;
- if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
+ /* Hide L1D cache contents from the nested guest. */
+ vmx->vcpu.arch.l1tf_flush_l1d = true;
+
+ /*
+ * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
+ * by event injection, halt vcpu.
+ */
+ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
+ !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK))
return kvm_vcpu_halt(vcpu);
vmx->nested.nested_run_pending = 1;
leave_guest_mode(vcpu);
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
if (likely(!vmx->fail)) {
if (exit_reason == -1)
sync_vmcs12(vcpu, vmcs12);
vmx_segment_cache_clear(vmx);
/* Update any VMCS fields that might have changed while L2 ran */
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
if (vmx->hv_deadline_tsc == -1)
vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
} else if (!nested_cpu_has_ept(vmcs12) &&
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+ trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
.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,
.vcpu_put = vmx_vcpu_put,
.update_bp_intercept = update_exception_bitmap,
+ .get_msr_feature = vmx_get_msr_feature,
.get_msr = vmx_get_msr,
.set_msr = vmx_set_msr,
.get_segment_base = vmx_get_segment_base,
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+ .read_l1_tsc_offset = vmx_read_l1_tsc_offset,
.write_tsc_offset = vmx_write_tsc_offset,
.set_tdp_cr3 = vmx_set_cr3,
.enable_smi_window = enable_smi_window,
};
-static int __init vmx_init(void)
+static void vmx_cleanup_l1d_flush(void)
{
- int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
- __alignof__(struct vcpu_vmx), THIS_MODULE);
- if (r)
- return r;
-
-#ifdef CONFIG_KEXEC_CORE
- rcu_assign_pointer(crash_vmclear_loaded_vmcss,
- crash_vmclear_local_loaded_vmcss);
-#endif
-
- return 0;
+ if (vmx_l1d_flush_pages) {
+ free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+ vmx_l1d_flush_pages = NULL;
+ }
+ /* Restore state so sysfs ignores VMX */
+ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
}
-static void __exit vmx_exit(void)
+static void vmx_exit(void)
{
#ifdef CONFIG_KEXEC_CORE
RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
#endif
kvm_exit();
+
+ vmx_cleanup_l1d_flush();
}
+module_exit(vmx_exit)
+static int __init vmx_init(void)
+{
+ int r;
+
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
+ if (r)
+ return r;
+
+ /*
+ * Must be called after kvm_init() so enable_ept is properly set
+ * up. Hand the parameter mitigation value in which was stored in
+ * the pre module init parser. If no parameter was given, it will
+ * contain 'auto' which will be turned into the default 'cond'
+ * mitigation mode.
+ */
+ if (boot_cpu_has(X86_BUG_L1TF)) {
+ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+ if (r) {
+ vmx_exit();
+ return r;
+ }
+ }
+
+#ifdef CONFIG_KEXEC_CORE
+ rcu_assign_pointer(crash_vmclear_loaded_vmcss,
+ crash_vmclear_local_loaded_vmcss);
+#endif
+
+ return 0;
+}
module_init(vmx_init)
-module_exit(vmx_exit)