#include <linux/tboot.h>
#include <linux/hrtimer.h>
#include <linux/frame.h>
+#include <linux/nospec.h>
#include "kvm_cache_regs.h"
#include "x86.h"
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
+#include <asm/microcode.h>
+#include <asm/spec-ctrl.h>
#include "trace.h"
#include "pmu.h"
static bool __read_mostly enable_pml = 1;
module_param_named(pml, enable_pml, bool, S_IRUGO);
+#define MSR_TYPE_R 1
+#define MSR_TYPE_W 2
+#define MSR_TYPE_RW 3
+
+#define MSR_BITMAP_MODE_X2APIC 1
+#define MSR_BITMAP_MODE_X2APIC_APICV 2
+#define MSR_BITMAP_MODE_LM 4
+
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
/* Guest_tsc -> host_tsc conversion requires 64-bit division. */
extern const ulong vmx_return;
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_always);
+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;
+ enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+ {"auto", VMENTER_L1D_FLUSH_AUTO},
+ {"never", VMENTER_L1D_FLUSH_NEVER},
+ {"cond", VMENTER_L1D_FLUSH_COND},
+ {"always", VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+#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 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_ALWAYS)
+ static_branch_enable(&vmx_l1d_flush_always);
+ else
+ static_branch_disable(&vmx_l1d_flush_always);
+ 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 (sysfs_streq(s, vmentry_l1d_param[i].option))
+ return vmentry_l1d_param[i].cmd;
+ }
+ }
+ return -EINVAL;
+}
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+ int l1tf, ret;
+
+ if (!boot_cpu_has(X86_BUG_L1TF))
+ return 0;
+
+ l1tf = vmentry_l1d_flush_parse(s);
+ if (l1tf < 0)
+ return l1tf;
+
+ /*
+ * 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)
+{
+ 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
-#define VMCS02_POOL_SIZE 1
struct vmcs {
u32 revision_id;
bool nmi_known_unmasked;
unsigned long vmcs_host_cr3; /* May not match real cr3 */
unsigned long vmcs_host_cr4; /* May not match real cr4 */
+ /* Support for vnmi-less CPUs */
+ int soft_vnmi_blocked;
+ ktime_t entry_time;
+ s64 vnmi_blocked_time;
+ unsigned long *msr_bitmap;
struct list_head loaded_vmcss_on_cpu_link;
};
* stored in guest memory specified by VMPTRLD, but is opaque to the guest,
* which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
* More than one of these structures may exist, if L1 runs multiple L2 guests.
- * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
+ * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
* underlying hardware which will be used to run L2.
* This structure is packed to ensure that its layout is identical across
* machines (necessary for live migration).
*/
#define VMCS12_SIZE 0x1000
-/* Used to remember the last vmcs02 used for some recently used vmcs12s */
-struct vmcs02_list {
- struct list_head list;
- gpa_t vmptr;
- struct loaded_vmcs vmcs02;
-};
-
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
*/
bool sync_shadow_vmcs;
- /* vmcs02_list cache of VMCSs recently used to run L2 guests */
- struct list_head vmcs02_pool;
- int vmcs02_num;
bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
+
+ struct loaded_vmcs vmcs02;
+
/*
- * Guest pages referred to in vmcs02 with host-physical pointers, so
- * we must keep them pinned while L2 runs.
+ * Guest pages referred to in the vmcs02 with host-physical
+ * pointers, so we must keep them pinned while L2 runs.
*/
struct page *apic_access_page;
struct page *virtual_apic_page;
bool pi_pending;
u16 posted_intr_nv;
- unsigned long *msr_bitmap;
-
struct hrtimer preemption_timer;
bool preemption_timer_expired;
(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;
u8 fail;
+ u8 msr_bitmap_mode;
u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
u64 msr_host_kernel_gs_base;
u64 msr_guest_kernel_gs_base;
#endif
+
+ u64 arch_capabilities;
+ u64 spec_ctrl;
+
u32 vm_entry_controls_shadow;
u32 vm_exit_controls_shadow;
u32 secondary_exec_control;
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;
static inline short vmcs_field_to_offset(unsigned long field)
{
- BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
+ const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
+ unsigned short offset;
- if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
- vmcs_field_to_offset_table[field] == 0)
+ BUILD_BUG_ON(size > SHRT_MAX);
+ if (field >= size)
return -ENOENT;
- return vmcs_field_to_offset_table[field];
+ field = array_index_nospec(field, size);
+ offset = vmcs_field_to_offset_table[field];
+ if (offset == 0)
+ return -ENOENT;
+ return offset;
}
static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
u16 error_code);
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
enum {
VMX_IO_BITMAP_A,
VMX_IO_BITMAP_B,
- VMX_MSR_BITMAP_LEGACY,
- VMX_MSR_BITMAP_LONGMODE,
- VMX_MSR_BITMAP_LEGACY_X2APIC_APICV,
- VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV,
- VMX_MSR_BITMAP_LEGACY_X2APIC,
- VMX_MSR_BITMAP_LONGMODE_X2APIC,
VMX_VMREAD_BITMAP,
VMX_VMWRITE_BITMAP,
VMX_BITMAP_NR
#define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A])
#define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B])
-#define vmx_msr_bitmap_legacy (vmx_bitmap[VMX_MSR_BITMAP_LEGACY])
-#define vmx_msr_bitmap_longmode (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE])
-#define vmx_msr_bitmap_legacy_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV])
-#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV])
-#define vmx_msr_bitmap_legacy_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC])
-#define vmx_msr_bitmap_longmode_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC])
#define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP])
#define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP])
(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;
SECONDARY_EXEC_ENABLE_INVPCID;
}
+static inline bool cpu_has_virtual_nmis(void)
+{
+ return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
+}
+
static inline bool cpu_has_vmx_wbinvd_exit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
(vmcs12->secondary_vm_exec_control & bit);
}
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
-{
- return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
-}
-
static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
{
return vmcs12->pin_based_vm_exec_control &
vmcs_write32(EXCEPTION_BITMAP, eb);
}
+/*
+ * Check if MSR is intercepted for currently loaded MSR bitmap.
+ */
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+{
+ unsigned long *msr_bitmap;
+ int f = sizeof(unsigned long);
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return true;
+
+ msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
+
+ if (msr <= 0x1fff) {
+ return !!test_bit(msr, msr_bitmap + 0x800 / f);
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+ }
+
+ return true;
+}
+
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+{
+ unsigned long *msr_bitmap;
+ int f = sizeof(unsigned long);
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return true;
+
+ msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+
+ if (msr <= 0x1fff) {
+ return !!test_bit(msr, msr_bitmap + 0x800 / f);
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+ }
+
+ return true;
+}
+
static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
unsigned long entry, unsigned long exit)
{
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;
if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
vmcs_load(vmx->loaded_vmcs->vmcs);
+ indirect_branch_prediction_barrier();
}
if (!already_loaded) {
* processors. See 22.2.4.
*/
vmcs_writel(HOST_TR_BASE,
- (unsigned long)this_cpu_ptr(&cpu_tss));
+ (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */
/*
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->guest_msrs[from] = tmp;
}
-static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
-{
- unsigned long *msr_bitmap;
-
- if (is_guest_mode(vcpu))
- msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
- else if (cpu_has_secondary_exec_ctrls() &&
- (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
- SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
- if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv;
- else
- msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv;
- } else {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
- else
- msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
- }
- } else {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode;
- else
- msr_bitmap = vmx_msr_bitmap_legacy;
- }
-
- vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-}
-
/*
* Set up the vmcs to automatically save and restore system
* msrs. Don't touch the 64-bit msrs if the guest is in legacy
vmx->save_nmsrs = save_nmsrs;
if (cpu_has_vmx_msr_bitmap())
- vmx_set_msr_bitmap(&vmx->vcpu);
+ vmx_update_msr_bitmap(&vmx->vcpu);
}
/*
* Advertise EPTP switching unconditionally
* since we emulate it
*/
- vmx->nested.nested_vmx_vmfunc_controls =
- VMX_VMFUNC_EPTP_SWITCHING;
+ if (enable_ept)
+ vmx->nested.nested_vmx_vmfunc_controls =
+ VMX_VMFUNC_EPTP_SWITCHING;
}
/*
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_SPEC_CTRL))
+ return 1;
+
+ msr_info->data = to_vmx(vcpu)->spec_ctrl;
+ break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+ return 1;
+ msr_info->data = to_vmx(vcpu)->arch_capabilities;
+ break;
case MSR_IA32_SYSENTER_CS:
msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
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_SPEC_CTRL))
+ return 1;
+
+ /* The STIBP bit doesn't fault even if it's not advertised */
+ if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+ return 1;
+
+ vmx->spec_ctrl = data;
+
+ if (!data)
+ break;
+
+ /*
+ * For non-nested:
+ * When it's written (to non-zero) for the first time, pass
+ * it through.
+ *
+ * For nested:
+ * The handling of the MSR bitmap for L2 guests is done in
+ * nested_vmx_merge_msr_bitmap. We should not touch the
+ * vmcs02.msr_bitmap here since it gets completely overwritten
+ * in the merging. We update the vmcs01 here for L1 as well
+ * since it will end up touching the MSR anyway now.
+ */
+ vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+ MSR_IA32_SPEC_CTRL,
+ MSR_TYPE_RW);
+ break;
+ case MSR_IA32_PRED_CMD:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+ return 1;
+
+ if (data & ~PRED_CMD_IBPB)
+ return 1;
+
+ if (!data)
+ break;
+
+ wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+
+ /*
+ * For non-nested:
+ * When it's written (to non-zero) for the first time, pass
+ * it through.
+ *
+ * For nested:
+ * The handling of the MSR bitmap for L2 guests is done in
+ * nested_vmx_merge_msr_bitmap. We should not touch the
+ * vmcs02.msr_bitmap here since it gets completely overwritten
+ * in the merging.
+ */
+ vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
+ MSR_TYPE_W);
+ break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated)
+ return 1;
+ vmx->arch_capabilities = data;
+ break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
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;
&_vmexit_control) < 0)
return -EIO;
- min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING |
- PIN_BASED_VIRTUAL_NMIS;
- opt = PIN_BASED_POSTED_INTR | PIN_BASED_VMX_PREEMPTION_TIMER;
+ min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
+ opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+ PIN_BASED_VMX_PREEMPTION_TIMER;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
&_pin_based_exec_control) < 0)
return -EIO;
return vmcs;
}
-static struct vmcs *alloc_vmcs(void)
-{
- return alloc_vmcs_cpu(raw_smp_processor_id());
-}
-
static void free_vmcs(struct vmcs *vmcs)
{
free_pages((unsigned long)vmcs, vmcs_config.order);
loaded_vmcs_clear(loaded_vmcs);
free_vmcs(loaded_vmcs->vmcs);
loaded_vmcs->vmcs = NULL;
+ if (loaded_vmcs->msr_bitmap)
+ free_page((unsigned long)loaded_vmcs->msr_bitmap);
WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
}
+static struct vmcs *alloc_vmcs(void)
+{
+ return alloc_vmcs_cpu(raw_smp_processor_id());
+}
+
+static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+ loaded_vmcs->vmcs = alloc_vmcs();
+ if (!loaded_vmcs->vmcs)
+ return -ENOMEM;
+
+ loaded_vmcs->shadow_vmcs = NULL;
+ loaded_vmcs_init(loaded_vmcs);
+
+ if (cpu_has_vmx_msr_bitmap()) {
+ loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!loaded_vmcs->msr_bitmap)
+ goto out_vmcs;
+ memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+ }
+ return 0;
+
+out_vmcs:
+ free_loaded_vmcs(loaded_vmcs);
+ return -ENOMEM;
+}
+
static void free_kvm_area(void)
{
int cpu;
spin_unlock(&vmx_vpid_lock);
}
-#define MSR_TYPE_R 1
-#define MSR_TYPE_W 2
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
- u32 msr, int type)
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type)
{
int f = sizeof(unsigned long);
}
}
+static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type)
+{
+ int f = sizeof(unsigned long);
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return;
+
+ /*
+ * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+ * have the write-low and read-high bitmap offsets the wrong way round.
+ * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+ */
+ if (msr <= 0x1fff) {
+ if (type & MSR_TYPE_R)
+ /* read-low */
+ __set_bit(msr, msr_bitmap + 0x000 / f);
+
+ if (type & MSR_TYPE_W)
+ /* write-low */
+ __set_bit(msr, msr_bitmap + 0x800 / f);
+
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ if (type & MSR_TYPE_R)
+ /* read-high */
+ __set_bit(msr, msr_bitmap + 0x400 / f);
+
+ if (type & MSR_TYPE_W)
+ /* write-high */
+ __set_bit(msr, msr_bitmap + 0xc00 / f);
+
+ }
+}
+
+static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type, bool value)
+{
+ if (value)
+ vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+ else
+ vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
+}
+
/*
* If a msr is allowed by L0, we should check whether it is allowed by L1.
* The corresponding bit will be cleared unless both of L0 and L1 allow it.
}
}
-static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
{
- if (!longmode_only)
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
- msr, MSR_TYPE_R | MSR_TYPE_W);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
- msr, MSR_TYPE_R | MSR_TYPE_W);
+ u8 mode = 0;
+
+ if (cpu_has_secondary_exec_ctrls() &&
+ (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
+ mode |= MSR_BITMAP_MODE_X2APIC;
+ if (enable_apicv && kvm_vcpu_apicv_active(vcpu))
+ mode |= MSR_BITMAP_MODE_X2APIC_APICV;
+ }
+
+ if (is_long_mode(vcpu))
+ mode |= MSR_BITMAP_MODE_LM;
+
+ return mode;
}
-static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active)
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
+static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
+ u8 mode)
{
- if (apicv_active) {
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv,
- msr, type);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv,
- msr, type);
- } else {
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, type);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, type);
+ int msr;
+
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+ msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
}
+
+ if (mode & MSR_BITMAP_MODE_X2APIC) {
+ /*
+ * TPR reads and writes can be virtualized even if virtual interrupt
+ * delivery is not in use.
+ */
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+ if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
+ vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+ }
+ }
+}
+
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+ u8 mode = vmx_msr_bitmap_mode(vcpu);
+ u8 changed = mode ^ vmx->msr_bitmap_mode;
+
+ if (!changed)
+ return;
+
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
+ !(mode & MSR_BITMAP_MODE_LM));
+
+ if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
+ vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+
+ vmx->msr_bitmap_mode = mode;
}
static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
if (is_guest_mode(vcpu) &&
vector == vmx->nested.posted_intr_nv) {
- /* the PIR and ON have been set by L1. */
- kvm_vcpu_trigger_posted_interrupt(vcpu, true);
/*
* If a posted intr is not recognized by hardware,
* we will accomplish it in the next vmentry.
*/
vmx->nested.pi_pending = true;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ /* the PIR and ON have been set by L1. */
+ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
+ kvm_vcpu_kick(vcpu);
return 0;
}
return -1;
}
if (cpu_has_vmx_msr_bitmap())
- vmx_set_msr_bitmap(vcpu);
+ vmx_update_msr_bitmap(vcpu);
}
static u32 vmx_exec_control(struct vcpu_vmx *vmx)
vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
}
if (cpu_has_vmx_msr_bitmap())
- vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
+ vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
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);
vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
u64 cr0;
vmx->rmode.vm86_active = 0;
+ vmx->spec_ctrl = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(vcpu, 0);
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
}
- vmcs_writel(GUEST_RFLAGS, 0x02);
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
vmcs_writel(GUEST_GDTR_BASE, 0);
static void enable_nmi_window(struct kvm_vcpu *vcpu)
{
- if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
+ if (!cpu_has_virtual_nmis() ||
+ vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
enable_irq_window(vcpu);
return;
}
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (!cpu_has_virtual_nmis()) {
+ /*
+ * Tracking the NMI-blocked state in software is built upon
+ * finding the next open IRQ window. This, in turn, depends on
+ * well-behaving guests: They have to keep IRQs disabled at
+ * least as long as the NMI handler runs. Otherwise we may
+ * cause NMI nesting, maybe breaking the guest. But as this is
+ * highly unlikely, we can live with the residual risk.
+ */
+ vmx->loaded_vmcs->soft_vnmi_blocked = 1;
+ vmx->loaded_vmcs->vnmi_blocked_time = 0;
+ }
+
++vcpu->stat.nmi_injections;
vmx->loaded_vmcs->nmi_known_unmasked = false;
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool masked;
+ if (!cpu_has_virtual_nmis())
+ return vmx->loaded_vmcs->soft_vnmi_blocked;
if (vmx->loaded_vmcs->nmi_known_unmasked)
return false;
masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->loaded_vmcs->nmi_known_unmasked = !masked;
- if (masked)
- vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
- else
- vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
+ if (!cpu_has_virtual_nmis()) {
+ if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) {
+ vmx->loaded_vmcs->soft_vnmi_blocked = masked;
+ vmx->loaded_vmcs->vnmi_blocked_time = 0;
+ }
+ } else {
+ vmx->loaded_vmcs->nmi_known_unmasked = !masked;
+ if (masked)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ else
+ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ }
}
static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
if (to_vmx(vcpu)->nested.nested_run_pending)
return 0;
+ if (!cpu_has_virtual_nmis() &&
+ to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked)
+ return 0;
+
return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
(GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI
| GUEST_INTR_STATE_NMI));
return 1; /* already handled by vmx_vcpu_run() */
if (is_invalid_opcode(intr_info)) {
- if (is_guest_mode(vcpu)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 1;
- }
er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+ if (er == EMULATE_USER_EXIT)
+ return 0;
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
(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);
* AAK134, BY25.
*/
if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ cpu_has_virtual_nmis() &&
(exit_qualification & INTR_INFO_UNBLOCK_NMI))
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
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);
if (kvm_test_request(KVM_REQ_EVENT, vcpu))
return 1;
- err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+ err = emulate_instruction(vcpu, 0);
if (err == EMULATE_USER_EXIT) {
++vcpu->stat.mmio_exits;
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)
static __init int hardware_setup(void)
{
- int r = -ENOMEM, i, msr;
+ int r = -ENOMEM, i;
rdmsrl_safe(MSR_EFER, &host_efer);
goto out;
}
- vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
- /*
- * Allow direct access to the PC debug port (it is often used for I/O
- * delays, but the vmexits simply slow things down).
- */
memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
- clear_bit(0x80, vmx_io_bitmap_a);
memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
- memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
- memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
goto out;
kvm_tsc_scaling_ratio_frac_bits = 48;
}
- vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-
- memcpy(vmx_msr_bitmap_legacy_x2apic_apicv,
- vmx_msr_bitmap_legacy, PAGE_SIZE);
- memcpy(vmx_msr_bitmap_longmode_x2apic_apicv,
- vmx_msr_bitmap_longmode, PAGE_SIZE);
- memcpy(vmx_msr_bitmap_legacy_x2apic,
- vmx_msr_bitmap_legacy, PAGE_SIZE);
- memcpy(vmx_msr_bitmap_longmode_x2apic,
- vmx_msr_bitmap_longmode, PAGE_SIZE);
-
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- for (msr = 0x800; msr <= 0x8ff; msr++) {
- if (msr == 0x839 /* TMCCT */)
- continue;
- vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true);
- }
-
- /*
- * TPR reads and writes can be virtualized even if virtual interrupt
- * delivery is not in use.
- */
- vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true);
- vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false);
-
- /* EOI */
- vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true);
- /* SELF-IPI */
- vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true);
-
if (enable_ept)
vmx_enable_tdp();
else
}
/*
- * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
- * We could reuse a single VMCS for all the L2 guests, but we also want the
- * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
- * allows keeping them loaded on the processor, and in the future will allow
- * optimizations where prepare_vmcs02 doesn't need to set all the fields on
- * every entry if they never change.
- * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
- * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
- *
- * The following functions allocate and free a vmcs02 in this pool.
- */
-
-/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
-static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
-{
- struct vmcs02_list *item;
- list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
- if (item->vmptr == vmx->nested.current_vmptr) {
- list_move(&item->list, &vmx->nested.vmcs02_pool);
- return &item->vmcs02;
- }
-
- if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
- /* Recycle the least recently used VMCS. */
- item = list_last_entry(&vmx->nested.vmcs02_pool,
- struct vmcs02_list, list);
- item->vmptr = vmx->nested.current_vmptr;
- list_move(&item->list, &vmx->nested.vmcs02_pool);
- return &item->vmcs02;
- }
-
- /* Create a new VMCS */
- item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
- if (!item)
- return NULL;
- item->vmcs02.vmcs = alloc_vmcs();
- item->vmcs02.shadow_vmcs = NULL;
- if (!item->vmcs02.vmcs) {
- kfree(item);
- return NULL;
- }
- loaded_vmcs_init(&item->vmcs02);
- item->vmptr = vmx->nested.current_vmptr;
- list_add(&(item->list), &(vmx->nested.vmcs02_pool));
- vmx->nested.vmcs02_num++;
- return &item->vmcs02;
-}
-
-/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
-static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
-{
- struct vmcs02_list *item;
- list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
- if (item->vmptr == vmptr) {
- free_loaded_vmcs(&item->vmcs02);
- list_del(&item->list);
- kfree(item);
- vmx->nested.vmcs02_num--;
- return;
- }
-}
-
-/*
- * Free all VMCSs saved for this vcpu, except the one pointed by
- * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
- * must be &vmx->vmcs01.
- */
-static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
-{
- struct vmcs02_list *item, *n;
-
- WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
- list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
- /*
- * Something will leak if the above WARN triggers. Better than
- * a use-after-free.
- */
- if (vmx->loaded_vmcs == &item->vmcs02)
- continue;
-
- free_loaded_vmcs(&item->vmcs02);
- list_del(&item->list);
- kfree(item);
- vmx->nested.vmcs02_num--;
- }
-}
-
-/*
* The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
* set the success or error code of an emulated VMX instruction, as specified
* by Vol 2B, VMX Instruction Reference, "Conventions".
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;
}
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs *shadow_vmcs;
+ int r;
- if (cpu_has_vmx_msr_bitmap()) {
- vmx->nested.msr_bitmap =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx->nested.msr_bitmap)
- goto out_msr_bitmap;
- }
+ r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
+ if (r < 0)
+ goto out_vmcs02;
vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
vmx->vmcs01.shadow_vmcs = shadow_vmcs;
}
- INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
- vmx->nested.vmcs02_num = 0;
-
hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+ vmx->nested.vpid02 = allocate_vpid();
+
vmx->nested.vmxon = true;
return 0;
kfree(vmx->nested.cached_vmcs12);
out_cached_vmcs12:
- free_page((unsigned long)vmx->nested.msr_bitmap);
+ free_loaded_vmcs(&vmx->nested.vmcs02);
-out_msr_bitmap:
+out_vmcs02:
return -ENOMEM;
}
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;
free_vpid(vmx->nested.vpid02);
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
- if (vmx->nested.msr_bitmap) {
- free_page((unsigned long)vmx->nested.msr_bitmap);
- vmx->nested.msr_bitmap = NULL;
- }
if (enable_shadow_vmcs) {
vmx_disable_shadow_vmcs(vmx);
vmcs_clear(vmx->vmcs01.shadow_vmcs);
vmx->vmcs01.shadow_vmcs = NULL;
}
kfree(vmx->nested.cached_vmcs12);
- /* Unpin physical memory we referred to in current vmcs02 */
+ /* Unpin physical memory we referred to in the vmcs02 */
if (vmx->nested.apic_access_page) {
kvm_release_page_dirty(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
vmx->nested.pi_desc = NULL;
}
- nested_free_all_saved_vmcss(vmx);
+ free_loaded_vmcs(&vmx->nested.vmcs02);
}
/* Emulate the VMXOFF instruction */
vmptr + offsetof(struct vmcs12, launch_state),
&zero, sizeof(zero));
- nested_free_vmcs02(vmx, vmptr);
-
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
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;
}
* "blocked by NMI" bit has to be set before next VM entry.
*/
if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ cpu_has_virtual_nmis() &&
(exit_qualification & INTR_INFO_UNBLOCK_NMI))
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
/*
* The host physical addresses of some pages of guest memory
- * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
- * may write to these pages via their host physical address while
- * L2 is running, bypassing any address-translation-based dirty
- * tracking (e.g. EPT write protection).
+ * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+ * Page). The CPU may write to these pages via their host
+ * physical address while L2 is running, bypassing any
+ * address-translation-based dirty tracking (e.g. EPT write
+ * protection).
*
* Mark them dirty on every exit from L2 to prevent them from
* getting out of sync with dirty tracking.
return 0;
}
+ if (unlikely(!cpu_has_virtual_nmis() &&
+ vmx->loaded_vmcs->soft_vnmi_blocked)) {
+ if (vmx_interrupt_allowed(vcpu)) {
+ vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+ } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL &&
+ vcpu->arch.nmi_pending) {
+ /*
+ * This CPU don't support us in finding the end of an
+ * NMI-blocked window if the guest runs with IRQs
+ * disabled. So we pull the trigger after 1 s of
+ * futile waiting, but inform the user about this.
+ */
+ printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
+ "state on VCPU %d after 1 s timeout\n",
+ __func__, vcpu->vcpu_id);
+ vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+ }
+ }
+
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
}
}
+/*
+ * 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_unlikely(&vmx_l1d_flush_always)) {
+ /*
+ * Clear the flush bit, it gets set again either from
+ * vcpu_run() or from one of the unsafe VMEXIT
+ * handlers.
+ */
+ vcpu->arch.l1tf_flush_l1d = false;
+ }
+
+ 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);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
- vmx_set_msr_bitmap(vcpu);
+ vmx_update_msr_bitmap(vcpu);
}
static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
#endif
"pushf\n\t"
__ASM_SIZE(push) " $%c[cs]\n\t"
- "call *%[entry]\n\t"
+ CALL_NOSPEC
:
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
ASM_CALL_CONSTRAINT
:
- [entry]"r"(entry),
+ THUNK_TARGET(entry),
[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)
idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
- if (vmx->loaded_vmcs->nmi_known_unmasked)
- return;
- /*
- * Can't use vmx->exit_intr_info since we're not sure what
- * the exit reason is.
- */
- exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
- vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
- /*
- * SDM 3: 27.7.1.2 (September 2008)
- * Re-set bit "block by NMI" before VM entry if vmexit caused by
- * a guest IRET fault.
- * SDM 3: 23.2.2 (September 2008)
- * Bit 12 is undefined in any of the following cases:
- * If the VM exit sets the valid bit in the IDT-vectoring
- * information field.
- * If the VM exit is due to a double fault.
- */
- if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
- vector != DF_VECTOR && !idtv_info_valid)
- vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
- else
- vmx->loaded_vmcs->nmi_known_unmasked =
- !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
- & GUEST_INTR_STATE_NMI);
+ if (cpu_has_virtual_nmis()) {
+ if (vmx->loaded_vmcs->nmi_known_unmasked)
+ return;
+ /*
+ * Can't use vmx->exit_intr_info since we're not sure what
+ * the exit reason is.
+ */
+ exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
+ vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
+ /*
+ * SDM 3: 27.7.1.2 (September 2008)
+ * Re-set bit "block by NMI" before VM entry if vmexit caused by
+ * a guest IRET fault.
+ * SDM 3: 23.2.2 (September 2008)
+ * Bit 12 is undefined in any of the following cases:
+ * If the VM exit sets the valid bit in the IDT-vectoring
+ * information field.
+ * If the VM exit is due to a double fault.
+ */
+ if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
+ vector != DF_VECTOR && !idtv_info_valid)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ else
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
+ & GUEST_INTR_STATE_NMI);
+ } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->vnmi_blocked_time +=
+ ktime_to_ns(ktime_sub(ktime_get(),
+ vmx->loaded_vmcs->entry_time));
}
static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
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)
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long debugctlmsr, cr3, cr4;
+ /* Record the guest's net vcpu time for enforced NMI injections. */
+ if (unlikely(!cpu_has_virtual_nmis() &&
+ vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->entry_time = ktime_get();
+
/* Don't enter VMX if guest state is invalid, let the exit handler
start emulation until we arrive back to a valid state */
if (vmx->emulation_required)
vmx_arm_hv_timer(vcpu);
+ /*
+ * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+ * it's non-zero. Since vmentry is serialising on affected CPUs, there
+ * is no need to worry about the conditional branch over the wrmsr
+ * being speculatively taken.
+ */
+ 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 ";"
/* Save guest registers, load host registers, keep flags */
"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
"pop %0 \n\t"
+ "setbe %c[fail](%0)\n\t"
"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
"mov %%r13, %c[r13](%0) \n\t"
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
+ "xor %%r8d, %%r8d \n\t"
+ "xor %%r9d, %%r9d \n\t"
+ "xor %%r10d, %%r10d \n\t"
+ "xor %%r11d, %%r11d \n\t"
+ "xor %%r12d, %%r12d \n\t"
+ "xor %%r13d, %%r13d \n\t"
+ "xor %%r14d, %%r14d \n\t"
+ "xor %%r15d, %%r15d \n\t"
#endif
"mov %%cr2, %%" _ASM_AX " \n\t"
"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
+ "xor %%eax, %%eax \n\t"
+ "xor %%ebx, %%ebx \n\t"
+ "xor %%esi, %%esi \n\t"
+ "xor %%edi, %%edi \n\t"
"pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t"
- "setbe %c[fail](%0) \n\t"
".pushsection .rodata \n\t"
".global vmx_return \n\t"
"vmx_return: " _ASM_PTR " 2b \n\t"
#endif
);
+ /*
+ * We do not use IBRS in the kernel. If this vCPU has used the
+ * SPEC_CTRL MSR it may have left it on; save the value and
+ * turn it off. This is much more efficient than blindly adding
+ * it to the atomic save/restore list. Especially as the former
+ * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+ *
+ * For non-nested case:
+ * If the L01 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ *
+ * For nested case:
+ * If the L02 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ */
+ 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, 0);
+
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
if (debugctlmsr)
update_debugctlmsr(debugctlmsr);
{
int err;
struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ unsigned long *msr_bitmap;
int cpu;
if (!vmx)
if (!vmx->guest_msrs)
goto free_pml;
- vmx->loaded_vmcs = &vmx->vmcs01;
- vmx->loaded_vmcs->vmcs = alloc_vmcs();
- vmx->loaded_vmcs->shadow_vmcs = NULL;
- if (!vmx->loaded_vmcs->vmcs)
+ err = alloc_loaded_vmcs(&vmx->vmcs01);
+ if (err < 0)
goto free_msrs;
- loaded_vmcs_init(vmx->loaded_vmcs);
+ msr_bitmap = vmx->vmcs01.msr_bitmap;
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+ vmx->msr_bitmap_mode = 0;
+
+ vmx->loaded_vmcs = &vmx->vmcs01;
cpu = get_cpu();
vmx_vcpu_load(&vmx->vcpu, cpu);
vmx->vcpu.cpu = cpu;
goto free_vmcs;
}
- if (nested) {
+ if (nested)
nested_vmx_setup_ctls_msrs(vmx);
- vmx->nested.vpid02 = allocate_vpid();
- }
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
return &vmx->vcpu;
free_vmcs:
- free_vpid(vmx->nested.vpid02);
free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
kfree(vmx->guest_msrs);
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;
if (cpu_has_vmx_msr_bitmap() &&
nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) &&
nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
- ;
+ vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_USE_MSR_BITMAPS);
else
vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
CPU_BASED_USE_MSR_BITMAPS);
int msr;
struct page *page;
unsigned long *msr_bitmap_l1;
- unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
+ unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+ /*
+ * pred_cmd & spec_ctrl are trying to verify two things:
+ *
+ * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+ * ensures that we do not accidentally generate an L02 MSR bitmap
+ * from the L12 MSR bitmap that is too permissive.
+ * 2. That L1 or L2s have actually used the MSR. This avoids
+ * unnecessarily merging of the bitmap if the MSR is unused. This
+ * works properly because we only update the L01 MSR bitmap lazily.
+ * So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+ * updated to reflect this when L1 (or its L2s) actually write to
+ * the MSR.
+ */
+ bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+ bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
- /* This shortcut is ok because we support only x2APIC MSRs so far. */
- if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
+ if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+ !pred_cmd && !spec_ctrl)
return false;
page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
MSR_TYPE_W);
}
}
+
+ if (spec_ctrl)
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_SPEC_CTRL,
+ MSR_TYPE_R | MSR_TYPE_W);
+
+ if (pred_cmd)
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_PRED_CMD,
+ MSR_TYPE_W);
+
kunmap(page);
kvm_release_page_clean(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
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
if (enable_vpid) {
/*
* There is no direct mapping between vpid02 and vpid12, the
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 vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- struct loaded_vmcs *vmcs02;
u32 msr_entry_idx;
u32 exit_qual;
- vmcs02 = nested_get_current_vmcs02(vmx);
- if (!vmcs02)
- return -ENOMEM;
-
enter_guest_mode(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
- vmx_switch_vmcs(vcpu, vmcs02);
+ vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
vmx_segment_cache_clear(vmx);
if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
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;
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qual;
-
- if (kvm_event_needs_reinjection(vcpu))
- return -EBUSY;
+ bool block_nested_events =
+ vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
if (vcpu->arch.exception.pending &&
nested_vmx_check_exception(vcpu, &exit_qual)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
- vcpu->arch.exception.pending = false;
return 0;
}
if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
vmx->nested.preemption_timer_expired) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
return 0;
}
if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
NMI_VECTOR | INTR_TYPE_NMI_INTR |
if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
nested_exit_on_intr(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
return 0;
kvm_clear_interrupt_queue(vcpu);
}
+static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u32 entry_failure_code;
+
+ nested_ept_uninit_mmu_context(vcpu);
+
+ /*
+ * Only PDPTE load can fail as the value of cr3 was checked on entry and
+ * couldn't have changed.
+ */
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+ if (!enable_ept)
+ vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+}
+
/*
* A part of what we need to when the nested L2 guest exits and we want to
* run its L1 parent, is to reset L1's guest state to the host state specified
struct vmcs12 *vmcs12)
{
struct kvm_segment seg;
- u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
- nested_ept_uninit_mmu_context(vcpu);
-
- /*
- * Only PDPTE load can fail as the value of cr3 was checked on entry and
- * couldn't have changed.
- */
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
- nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
- if (!enable_ept)
- vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
if (enable_vpid) {
/*
vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
+ vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF);
+ vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF);
/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1. */
if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
if (cpu_has_vmx_msr_bitmap())
- vmx_set_msr_bitmap(vcpu);
+ vmx_update_msr_bitmap(vcpu);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))
vm_exit_controls_reset_shadow(vmx);
vmx_segment_cache_clear(vmx);
- /* if no vmcs02 cache requested, remove the one we used */
- if (VMCS02_POOL_SIZE == 0)
- nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
-
/* 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,
* accordingly.
*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+ load_vmcs12_mmu_host_state(vcpu, vmcs12);
+
/*
* The emulated instruction was already skipped in
* nested_vmx_run, but the updated RIP was never
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,
.setup_mce = vmx_setup_mce,
};
-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)