struct list_head vmcs02_pool;
int vmcs02_num;
u64 vmcs01_tsc_offset;
+ bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
/*
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
}
-static inline bool is_exception(u32 intr_info)
+static inline bool is_nmi(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
- == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
+ == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
}
static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
return;
}
break;
+ case MSR_IA32_PEBS_ENABLE:
+ /* PEBS needs a quiescent period after being disabled (to write
+ * a record). Disabling PEBS through VMX MSR swapping doesn't
+ * provide that period, so a CPU could write host's record into
+ * guest's memory.
+ */
+ wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
for (i = 0; i < m->nr; ++i)
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
- u64 guest_efer;
- u64 ignore_bits;
+ u64 guest_efer = vmx->vcpu.arch.efer;
+ u64 ignore_bits = 0;
- guest_efer = vmx->vcpu.arch.efer;
+ if (!enable_ept) {
+ /*
+ * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing
+ * host CPUID is more efficient than testing guest CPUID
+ * or CR4. Host SMEP is anyway a requirement for guest SMEP.
+ */
+ if (boot_cpu_has(X86_FEATURE_SMEP))
+ guest_efer |= EFER_NX;
+ else if (!(guest_efer & EFER_NX))
+ ignore_bits |= EFER_NX;
+ }
/*
- * NX is emulated; LMA and LME handled by hardware; SCE meaningless
- * outside long mode
+ * LMA and LME handled by hardware; SCE meaningless outside long mode.
*/
- ignore_bits = EFER_NX | EFER_SCE;
+ ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
- vmx->guest_msrs[efer_offset].data = guest_efer;
- vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
*/
if (cpu_has_load_ia32_efer ||
(enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
- guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer);
return false;
- }
+ } else {
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
- return true;
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ return true;
+ }
}
static unsigned long segment_base(u16 selector)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
} else
vmx->nested.nested_vmx_ept_caps = 0;
+ /*
+ * Old versions of KVM use the single-context version without
+ * checking for support, so declare that it is supported even
+ * though it is treated as global context. The alternative is
+ * not failing the single-context invvpid, and it is worse.
+ */
if (enable_vpid)
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+ VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
else
vmx->nested.nested_vmx_vpid_caps = 0;
msr_info->data = vcpu->arch.ia32_xss;
break;
case MSR_TSC_AUX:
- if (!guest_cpuid_has_rdtscp(vcpu))
+ if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
return 1;
/* Otherwise falls through */
default:
clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
break;
case MSR_TSC_AUX:
- if (!guest_cpuid_has_rdtscp(vcpu))
+ if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
return 1;
/* Check reserved bit, higher 32 bits should be zero */
if ((data >> 32) != 0)
}
vmcs_write16(sf->selector, var.selector);
- vmcs_write32(sf->base, var.base);
+ vmcs_writel(sf->base, var.base);
vmcs_write32(sf->limit, var.limit);
vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
}
if (vmx_xsaves_supported())
vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
+ if (enable_pml) {
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
return 0;
}
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx_set_cr4(vcpu, 0);
vmx_set_efer(vcpu, 0);
vmx_fpu_activate(vcpu);
if (is_machine_check(intr_info))
return handle_machine_check(vcpu);
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
+ if (is_nmi(intr_info))
return 1; /* already handled by vmx_vcpu_run() */
if (is_no_device(intr_info)) {
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);
}
page = nested_get_page(vcpu, vmptr);
- if (page == NULL ||
- *(u32 *)kmap(page) != VMCS12_REVISION) {
+ if (page == NULL) {
nested_vmx_failInvalid(vcpu);
+ skip_emulated_instruction(vcpu);
+ return 1;
+ }
+ if (*(u32 *)kmap(page) != VMCS12_REVISION) {
kunmap(page);
+ nested_release_page_clean(page);
+ nested_vmx_failInvalid(vcpu);
skip_emulated_instruction(vcpu);
return 1;
}
kunmap(page);
+ nested_release_page_clean(page);
vmx->nested.vmxon_ptr = vmptr;
break;
case EXIT_REASON_VMCLEAR:
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
if (!(types & (1UL << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ skip_emulated_instruction(vcpu);
return 1;
}
}
switch (type) {
+ case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+ /*
+ * Old versions of KVM use the single-context version so we
+ * have to support it; just treat it the same as all-context.
+ */
case VMX_VPID_EXTENT_ALL_CONTEXT:
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
nested_vmx_succeed(vcpu);
break;
default:
- /* Trap single context invalidation invvpid calls */
+ /* Trap individual address invalidation invvpid calls */
BUG_ON(1);
break;
}
switch (exit_reason) {
case EXIT_REASON_EXCEPTION_NMI:
- if (!is_exception(intr_info))
+ if (is_nmi(intr_info))
return false;
else if (is_page_fault(intr_info))
return enable_ept;
case EXIT_REASON_TASK_SWITCH:
return true;
case EXIT_REASON_CPUID:
- if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
- return false;
return true;
case EXIT_REASON_HLT:
return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
case EXIT_REASON_PCOMMIT:
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
+ case EXIT_REASON_PML_FULL:
+ /* We don't expose PML support to L1. */
+ return false;
default:
return true;
}
*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
}
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
- struct page *pml_pg;
-
- pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!pml_pg)
- return -ENOMEM;
-
- vmx->pml_pg = pml_pg;
-
- vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
- vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
- return 0;
-}
-
static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
{
if (vmx->pml_pg) {
static void vmx_dump_sel(char *name, uint32_t sel)
{
pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
- name, vmcs_read32(sel),
+ name, vmcs_read16(sel),
vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
+ trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
+
/*
* Flush logged GPAs PML buffer, this will make dirty_bitmap more
* updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
exit_reason != EXIT_REASON_EPT_VIOLATION &&
+ exit_reason != EXIT_REASON_PML_FULL &&
exit_reason != EXIT_REASON_TASK_SWITCH)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
{
u32 sec_exec_control;
+ /* Postpone execution until vmcs01 is the current VMCS. */
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ return;
+ }
+
/*
* There is not point to enable virtualize x2apic without enable
* apicv
kvm_machine_check();
/* We need to handle NMIs before interrupts are enabled */
- if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
- (exit_intr_info & INTR_INFO_VALID_MASK)) {
+ if (is_nmi(exit_intr_info)) {
kvm_before_handle_nmi(&vmx->vcpu);
asm("int $2");
kvm_after_handle_nmi(&vmx->vcpu);
vmx->loaded_vmcs->launched = 1;
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
- trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
/*
* the KVM_REQ_EVENT optimization bit is only on for one entry, and if
put_cpu();
}
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int r;
+
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
+ vmx_load_vmcs01(vcpu);
+ free_nested(vmx);
+ vcpu_put(vcpu);
+}
+
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmx_destroy_pml_buffer(vmx);
free_vpid(vmx->vpid);
leave_guest_mode(vcpu);
- vmx_load_vmcs01(vcpu);
- free_nested(vmx);
+ vmx_free_vcpu_nested(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
if (err)
goto free_vcpu;
+ err = -ENOMEM;
+
+ /*
+ * If PML is turned on, failure on enabling PML just results in failure
+ * of creating the vcpu, therefore we can simplify PML logic (by
+ * avoiding dealing with cases, such as enabling PML partially on vcpus
+ * for the guest, etc.
+ */
+ if (enable_pml) {
+ vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!vmx->pml_pg)
+ goto uninit_vcpu;
+ }
+
vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
> PAGE_SIZE);
- err = -ENOMEM;
- if (!vmx->guest_msrs) {
- goto uninit_vcpu;
- }
+ if (!vmx->guest_msrs)
+ goto free_pml;
vmx->loaded_vmcs = &vmx->vmcs01;
vmx->loaded_vmcs->vmcs = alloc_vmcs();
vmx->nested.current_vmptr = -1ull;
vmx->nested.current_vmcs12 = NULL;
- /*
- * If PML is turned on, failure on enabling PML just results in failure
- * of creating the vcpu, therefore we can simplify PML logic (by
- * avoiding dealing with cases, such as enabling PML partially on vcpus
- * for the guest, etc.
- */
- if (enable_pml) {
- err = vmx_create_pml_buffer(vmx);
- if (err)
- goto free_vmcs;
- }
-
return &vmx->vcpu;
free_vmcs:
free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
kfree(vmx->guest_msrs);
+free_pml:
+ vmx_destroy_pml_buffer(vmx);
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
best->ebx &= ~bit(X86_FEATURE_INVPCID);
}
- vmcs_set_secondary_exec_control(secondary_exec_ctl);
+ if (cpu_has_secondary_exec_ctrls())
+ vmcs_set_secondary_exec_control(secondary_exec_ctl);
if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
if (guest_cpuid_has_pcommit(vcpu))
}
+ if (enable_pml) {
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit, this happens
+ * to be equivalent to simply resetting the fields in vmcs02.
+ */
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
/* Update TSC_OFFSET if TSC was changed while L2 ran */
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+ vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+ vmx_set_virtual_x2apic_mode(vcpu,
+ vcpu->arch.apic_base & X2APIC_ENABLE);
+ }
+
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;