#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
+#include <asm/microcode.h>
#include "trace.h"
#include "pmu.h"
struct vmcs *vmcs;
struct vmcs *shadow_vmcs;
int cpu;
- int launched;
+ bool launched;
+ 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;
struct list_head loaded_vmcss_on_cpu_link;
};
/* The guest-physical address of the current VMCS L1 keeps for L2 */
gpa_t current_vmptr;
- /* The host-usable pointer to the above */
- struct page *current_vmcs12_page;
- struct vmcs12 *current_vmcs12;
/*
* Cache of the guest's VMCS, existing outside of guest memory.
* Loaded from guest memory during VMPTRLD. Flushed to guest
- * memory during VMXOFF, VMCLEAR, VMPTRLD.
+ * memory during VMCLEAR and VMPTRLD.
*/
struct vmcs12 *cached_vmcs12;
/*
struct kvm_vcpu vcpu;
unsigned long host_rsp;
u8 fail;
- bool nmi_known_unmasked;
u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
int gs_ldt_reload_needed;
int fs_reload_needed;
u64 msr_host_bndcfgs;
- unsigned long vmcs_host_cr3; /* May not match real cr3 */
- unsigned long vmcs_host_cr4; /* May not match real cr4 */
} host_state;
struct {
int vm86_active;
u64 current_tsc_ratio;
- bool guest_pkru_valid;
- u32 guest_pkru;
u32 host_pkru;
/*
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
static int alloc_identity_pagetable(struct kvm *kvm);
+static bool vmx_get_nmi_mask(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 DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
(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 &
if (error)
printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
vmcs, phys_addr);
+
}
#ifdef CONFIG_KEXEC_CORE
struct pi_desc old, new;
unsigned int dest;
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ /*
+ * In case of hot-plug or hot-unplug, we may have to undo
+ * vmx_vcpu_pi_put even if there is no assigned device. And we
+ * always keep PI.NDST up to date for simplicity: it makes the
+ * code easier, and CPU migration is not a fast path.
+ */
+ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
return;
+ /*
+ * First handle the simple case where no cmpxchg is necessary; just
+ * allow posting non-urgent interrupts.
+ *
+ * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+ * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+ * expects the VCPU to be on the blocked_vcpu_list that matches
+ * PI.NDST.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+ vcpu->cpu == cpu) {
+ pi_clear_sn(pi_desc);
+ return;
+ }
+
+ /* The full case. */
do {
old.control = new.control = pi_desc->control;
- /*
- * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
- * are two possible cases:
- * 1. After running 'pre_block', context switch
- * happened. For this case, 'sn' was set in
- * vmx_vcpu_put(), so we need to clear it here.
- * 2. After running 'pre_block', we were blocked,
- * and woken up by some other guy. For this case,
- * we don't need to do anything, 'pi_post_block'
- * will do everything for us. However, we cannot
- * check whether it is case #1 or case #2 here
- * (maybe, not needed), so we also clear sn here,
- * I think it is not a big deal.
- */
- if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
- if (vcpu->cpu != cpu) {
- dest = cpu_physical_id(cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
- }
+ dest = cpu_physical_id(cpu);
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- }
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
- /* Allow posting non-urgent interrupts */
new.sn = 0;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
}
static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
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);
+ if (ibpb_inuse)
+ native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
}
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 */
/*
__vmx_load_host_state(to_vmx(vcpu));
}
+static bool emulation_required(struct kvm_vcpu *vcpu)
+{
+ return emulate_invalid_guest_state && !guest_state_valid(vcpu);
+}
+
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
/*
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
+ unsigned long old_rflags = vmx_get_rflags(vcpu);
+
__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
to_vmx(vcpu)->rflags = rflags;
if (to_vmx(vcpu)->rmode.vm86_active) {
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
}
vmcs_writel(GUEST_RFLAGS, rflags);
-}
-static u32 vmx_get_pkru(struct kvm_vcpu *vcpu)
-{
- return to_vmx(vcpu)->guest_pkru;
+ if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
+ to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
}
static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
vmx_set_interrupt_shadow(vcpu, 0);
}
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+ unsigned long exit_qual)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ unsigned int nr = vcpu->arch.exception.nr;
+ u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+ if (vcpu->arch.exception.has_error_code) {
+ vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+ intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+ }
+
+ if (kvm_exception_is_soft(nr))
+ intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+ else
+ intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+ if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+ vmx_get_nmi_mask(vcpu))
+ intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
/*
* KVM wants to inject page-faults which it got to the guest. This function
* checks whether in a nested guest, we need to inject them to L1 or L2.
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
unsigned int nr = vcpu->arch.exception.nr;
- if (!((vmcs12->exception_bitmap & (1u << nr)) ||
- (nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
- return 0;
+ if (nr == PF_VECTOR) {
+ if (vcpu->arch.exception.nested_apf) {
+ nested_vmx_inject_exception_vmexit(vcpu,
+ vcpu->arch.apf.nested_apf_token);
+ return 1;
+ }
+ /*
+ * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
+ * The fix is to add the ancillary datum (CR2 or DR6) to structs
+ * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
+ * can be written only when inject_pending_event runs. This should be
+ * conditional on a new capability---if the capability is disabled,
+ * kvm_multiple_exception would write the ancillary information to
+ * CR2 or DR6, for backwards ABI-compatibility.
+ */
+ if (nested_vmx_is_page_fault_vmexit(vmcs12,
+ vcpu->arch.exception.error_code)) {
+ nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+ return 1;
+ }
+ } else {
+ unsigned long exit_qual = 0;
+ if (nr == DB_VECTOR)
+ exit_qual = vcpu->arch.dr6;
- if (vcpu->arch.exception.nested_apf) {
- vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
- nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
- PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
- INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
- vcpu->arch.apf.nested_apf_token);
- return 1;
+ if (vmcs12->exception_bitmap & (1u << nr)) {
+ nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ return 1;
+ }
}
- nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- return 1;
+ return 0;
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu)
* reason is that if one of these bits is necessary, it will appear
* in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
* fields of vmcs01 and vmcs02, will turn these bits off - and
- * nested_vmx_exit_handled() will not pass related exits to L1.
+ * nested_vmx_exit_reflected() will not pass related exits to L1.
* These rules have exceptions below.
*/
case MSR_IA32_TSC:
msr_info->data = guest_read_tsc(vcpu);
break;
+ case MSR_IA32_SPEC_CTRL:
+ msr_info->data = vcpu->arch.spec_ctrl;
+ 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:
+ vcpu->arch.spec_ctrl = msr_info->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))
&_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 0;
}
-static bool emulation_required(struct kvm_vcpu *vcpu)
-{
- return emulate_invalid_guest_state && !guest_state_valid(vcpu);
-}
-
static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
struct kvm_segment *save)
{
return enable_apicv;
}
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ gfn_t gfn;
+
+ /*
+ * Don't need to mark the APIC access page dirty; it is never
+ * written to by the CPU during APIC virtualization.
+ */
+
+ if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+ gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
+ }
+
+ if (nested_cpu_has_posted_intr(vmcs12)) {
+ gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
+ }
+}
+
+
static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
void *vapic_page;
u16 status;
- if (vmx->nested.pi_desc &&
- vmx->nested.pi_pending) {
- vmx->nested.pi_pending = false;
- if (!pi_test_and_clear_on(vmx->nested.pi_desc))
- return;
-
- max_irr = find_last_bit(
- (unsigned long *)vmx->nested.pi_desc->pir, 256);
+ if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+ return;
- if (max_irr == 256)
- return;
+ vmx->nested.pi_pending = false;
+ if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+ return;
+ max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+ if (max_irr != 256) {
vapic_page = kmap(vmx->nested.virtual_apic_page);
__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
kunmap(vmx->nested.virtual_apic_page);
vmcs_write16(GUEST_INTR_STATUS, status);
}
}
+
+ nested_mark_vmcs12_pages_dirty(vcpu);
}
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+ bool nested)
{
#ifdef CONFIG_SMP
- if (vcpu->mode == IN_GUEST_MODE) {
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
+ if (vcpu->mode == IN_GUEST_MODE) {
/*
- * Currently, we don't support urgent interrupt,
- * all interrupts are recognized as non-urgent
- * interrupt, so we cannot post interrupts when
- * 'SN' is set.
+ * The vector of interrupt to be delivered to vcpu had
+ * been set in PIR before this function.
+ *
+ * Following cases will be reached in this block, and
+ * we always send a notification event in all cases as
+ * explained below.
+ *
+ * Case 1: vcpu keeps in non-root mode. Sending a
+ * notification event posts the interrupt to vcpu.
*
- * If the vcpu is in guest mode, it means it is
- * running instead of being scheduled out and
- * waiting in the run queue, and that's the only
- * case when 'SN' is set currently, warning if
- * 'SN' is set.
+ * Case 2: vcpu exits to root mode and is still
+ * runnable. PIR will be synced to vIRR before the
+ * next vcpu entry. Sending a notification event in
+ * this case has no effect, as vcpu is not in root
+ * mode.
+ *
+ * Case 3: vcpu exits to root mode and is blocked.
+ * vcpu_block() has already synced PIR to vIRR and
+ * never blocks vcpu if vIRR is not cleared. Therefore,
+ * a blocked vcpu here does not wait for any requested
+ * interrupts in PIR, and sending a notification event
+ * which has no effect is safe here.
*/
- WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
- apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
- POSTED_INTR_VECTOR);
+ apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
return true;
}
#endif
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);
+ kvm_vcpu_trigger_posted_interrupt(vcpu, true);
/*
* If a posted intr is not recognized by hardware,
* we will accomplish it in the next vmentry.
if (pi_test_and_set_on(&vmx->pi_desc))
return;
- if (!kvm_vcpu_trigger_posted_interrupt(vcpu))
+ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
kvm_vcpu_kick(vcpu);
}
*/
cr3 = __read_cr3();
vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
/* Save the most likely value for this task's CR4 in the VMCS. */
cr4 = cr4_read_shadow();
vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
#ifdef CONFIG_X86_64
vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
- native_store_idt(&dt);
+ store_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
vmx->host_idt_base = dt.address;
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 (!is_guest_mode(vcpu)) {
- ++vcpu->stat.nmi_injections;
- vmx->nmi_known_unmasked = false;
+ 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;
+
if (vmx->rmode.vm86_active) {
if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
{
- if (to_vmx(vcpu)->nmi_known_unmasked)
+ 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;
- return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
+ masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
+ vmx->loaded_vmcs->nmi_known_unmasked = !masked;
+ return masked;
}
static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->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));
(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);
msr_info.index = ecx;
msr_info.host_initiated = false;
+
if (vmx_get_msr(vcpu, &msr_info)) {
trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(vcpu, 0);
* 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);
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);
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);
+ vmx_disable_intercept_for_msr(MSR_IA32_SPEC_CTRL, false);
+ vmx_disable_intercept_for_msr(MSR_IA32_PRED_CMD, false);
memcpy(vmx_msr_bitmap_legacy_x2apic_apicv,
vmx_msr_bitmap_legacy, PAGE_SIZE);
}
/* Create a new VMCS */
- item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
+ item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
if (!item)
return NULL;
item->vmcs02.vmcs = alloc_vmcs();
return 1;
}
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
{
if (vmx->nested.current_vmptr == -1ull)
return;
- /* current_vmptr and current_vmcs12 are always set/reset together */
- if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
- return;
-
if (enable_shadow_vmcs) {
/* copy to memory all shadowed fields in case
they were modified */
copy_shadow_to_vmcs12(vmx);
vmx->nested.sync_shadow_vmcs = false;
- vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_SHADOW_VMCS);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);
+ vmx_disable_shadow_vmcs(vmx);
}
vmx->nested.posted_intr_nv = -1;
/* Flush VMCS12 to guest memory */
- memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
- VMCS12_SIZE);
+ kvm_vcpu_write_guest_page(&vmx->vcpu,
+ vmx->nested.current_vmptr >> PAGE_SHIFT,
+ vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
- kunmap(vmx->nested.current_vmcs12_page);
- nested_release_page(vmx->nested.current_vmcs12_page);
vmx->nested.current_vmptr = -1ull;
- vmx->nested.current_vmcs12 = NULL;
}
/*
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
- nested_release_vmcs12(vmx);
+ 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);
free_vmcs(vmx->vmcs01.shadow_vmcs);
vmx->vmcs01.shadow_vmcs = NULL;
}
nested_release_vmcs12(vmx);
- vmx->nested.current_vmcs12 = new_vmcs12;
- vmx->nested.current_vmcs12_page = page;
/*
* Load VMCS12 from guest memory since it is not already
* cached.
*/
- memcpy(vmx->nested.cached_vmcs12,
- vmx->nested.current_vmcs12, VMCS12_SIZE);
+ memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+ kunmap(page);
+ nested_release_page_clean(page);
+
set_current_vmptr(vmx, vmptr);
}
* "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);
* should handle it ourselves in L0 (and then continue L2). Only call this
* when in is_guest_mode (L2).
*/
-static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
{
u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- u32 exit_reason = vmx->exit_reason;
trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
vmcs_readl(EXIT_QUALIFICATION),
vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
KVM_ISA_VMX);
+ /*
+ * 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).
+ *
+ * Mark them dirty on every exit from L2 to prevent them from
+ * getting out of sync with dirty tracking.
+ */
+ nested_mark_vmcs12_pages_dirty(vcpu);
+
if (vmx->nested.nested_run_pending)
return false;
}
}
+static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+ u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+ /*
+ * At this point, the exit interruption info in exit_intr_info
+ * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT
+ * we need to query the in-kernel LAPIC.
+ */
+ WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+ if ((exit_intr_info &
+ (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+ (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ vmcs12->vm_exit_intr_error_code =
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+ }
+
+ nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+ vmcs_readl(EXIT_QUALIFICATION));
+ return 1;
+}
+
static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
{
*info1 = vmcs_readl(EXIT_QUALIFICATION);
if (vmx->emulation_required)
return handle_invalid_guest_state(vcpu);
- if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
- nested_vmx_vmexit(vcpu, exit_reason,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- return 1;
- }
+ if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+ return nested_vmx_reflect_vmexit(vcpu, exit_reason);
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
dump_vmcs();
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);
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- register void *__sp asm(_ASM_SP);
if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
desc = (gate_desc *)vmx->host_idt_base + vector;
- entry = gate_offset(*desc);
+ entry = gate_offset(desc);
asm volatile(
#ifdef CONFIG_X86_64
"mov %%" _ASM_SP ", %[sp]\n\t"
#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
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
:
- [entry]"r"(entry),
+ THUNK_TARGET(entry),
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
- if (vmx->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->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,
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)
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
cr3 = __get_current_cr3_fast();
- if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+ if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
vmcs_writel(HOST_CR3, cr3);
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
}
cr4 = cr4_read_shadow();
- if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+ if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
vmcs_writel(HOST_CR4, cr4);
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
}
/* When single-stepping over STI and MOV SS, we must clear the
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
- if (vmx->guest_pkru_valid)
- __write_pkru(vmx->guest_pkru);
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+ vcpu->arch.pkru != vmx->host_pkru)
+ __write_pkru(vcpu->arch.pkru);
atomic_switch_perf_msrs(vmx);
+
+ /* SMB: Ignore ibrs_inuse but rely on vcpu value */
+ x86_spec_ctrl_set_guest(vcpu->arch.spec_ctrl);
+
debugctlmsr = get_debugctlmsr();
vmx_arm_hv_timer(vcpu);
/* 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
);
+ x86_spec_ctrl_restore_host(vcpu->arch.spec_ctrl);
+
+ /* 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);
* back on host, so it is safe to read guest PKRU from current
* XSAVE.
*/
- if (boot_cpu_has(X86_FEATURE_OSPKE)) {
- vmx->guest_pkru = __read_pkru();
- if (vmx->guest_pkru != vmx->host_pkru) {
- vmx->guest_pkru_valid = true;
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
+ vcpu->arch.pkru = __read_pkru();
+ if (vcpu->arch.pkru != vmx->host_pkru)
__write_pkru(vmx->host_pkru);
- } else
- vmx->guest_pkru_valid = false;
}
/*
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
- vmx->nested.current_vmcs12 = NULL;
vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+ /*
+ * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+ * or POSTED_INTR_WAKEUP_VECTOR.
+ */
+ vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+ vmx->pi_desc.sn = 1;
+
return &vmx->vcpu;
free_vmcs:
WARN_ON(!is_guest_mode(vcpu));
- if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code))
- nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
- else
+ if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+ vmcs12->vm_exit_intr_error_code = fault->error_code;
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+ PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+ INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+ fault->address);
+ } else {
kvm_inject_page_fault(vcpu, fault);
+ }
}
static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
vmcs12->vm_entry_instruction_len);
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
vmcs12->guest_interruptibility_info);
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
} else {
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
/* Posted interrupts setting is only taken from vmcs12. */
if (nested_cpu_has_posted_intr(vmcs12)) {
- /*
- * Note that we use L0's vector here and in
- * vmx_deliver_nested_posted_interrupt.
- */
vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
vmx->nested.pi_pending = false;
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
} else {
exec_control &= ~PIN_BASED_POSTED_INTR;
}
* "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
* vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
* !enable_ept, EB.PF is 1, so the "or" will always be 1.
- *
- * A problem with this approach (when !enable_ept) is that L1 may be
- * injected with more page faults than it asked for. This could have
- * caused problems, but in practice existing hypervisors don't care.
- * To fix this, we will need to emulate the PFEC checking (on the L1
- * page tables), using walk_addr(), when injecting PFs to L1.
*/
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
enable_ept ? vmcs12->page_fault_error_code_mask : 0);
if (exec_control & CPU_BASED_TPR_SHADOW) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ } else {
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING;
+#endif
}
/*
{
struct vmcs12 *vmcs12;
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
u32 exit_qual;
int ret;
* for misconfigurations which will anyway be caught by the processor
* when using the merged vmcs02.
*/
+ if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
+ nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
+ goto out;
+ }
+
if (vmcs12->launch_state == launch) {
nested_vmx_failValid(vcpu,
launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
vmcs12->vm_exit_reason = exit_reason;
vmcs12->exit_qualification = exit_qualification;
-
vmcs12->vm_exit_intr_info = exit_intr_info;
- if ((vmcs12->vm_exit_intr_info &
- (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
- (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK))
- vmcs12->vm_exit_intr_error_code =
- vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
vmcs12->idt_vectoring_info_field = 0;
vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
/* Same as above - no reason to call set_cr4_guest_host_mask(). */
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
- kvm_set_cr4(vcpu, vmcs12->host_cr4);
+ vmx_set_cr4(vcpu, vmcs12->host_cr4);
nested_ept_uninit_mmu_context(vcpu);
*/
vmx_flush_tlb(vcpu);
}
-
+ /* Restore posted intr vector. */
+ if (nested_cpu_has_posted_intr(vmcs12))
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
- && nested_exit_intr_ack_set(vcpu)) {
+ /*
+ * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of
+ * the VM-exit interrupt information (valid interrupt) is always set to
+ * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need
+ * kvm_cpu_has_interrupt(). See the commit message for details.
+ */
+ if (nested_exit_intr_ack_set(vcpu) &&
+ exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+ kvm_cpu_has_interrupt(vcpu)) {
int irq = kvm_cpu_get_interrupt(vcpu);
WARN_ON(irq < 0);
vmcs12->vm_exit_intr_info = irq |
kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
}
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct pi_desc old, new;
+ unsigned int dest;
+
+ do {
+ old.control = new.control = pi_desc->control;
+ WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the VCPU is blocked\n");
+
+ dest = cpu_physical_id(vcpu->cpu);
+
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
+
+ /* set 'NV' to 'notification vector' */
+ new.nv = POSTED_INTR_VECTOR;
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
+
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_del(&vcpu->blocked_vcpu_list);
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ vcpu->pre_pcpu = -1;
+ }
+}
+
/*
* This routine does the following things for vCPU which is going
* to be blocked if VT-d PI is enabled.
*/
static int pi_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
!kvm_vcpu_apicv_active(vcpu))
return 0;
- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+ vcpu->pre_pcpu = vcpu->cpu;
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu,
+ vcpu->pre_pcpu));
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ }
do {
old.control = new.control = pi_desc->control;
- /*
- * We should not block the vCPU if
- * an interrupt is posted for it.
- */
- if (pi_test_on(pi_desc) == 1) {
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
-
- return 1;
- }
-
WARN((pi_desc->sn == 1),
"Warning: SN field of posted-interrupts "
"is set before blocking\n");
/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
- return 0;
+ /* We should not block the vCPU if an interrupt is posted for it. */
+ if (pi_test_on(pi_desc) == 1)
+ __pi_post_block(vcpu);
+
+ local_irq_enable();
+ return (vcpu->pre_pcpu == -1);
}
static int vmx_pre_block(struct kvm_vcpu *vcpu)
static void pi_post_block(struct kvm_vcpu *vcpu)
{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct pi_desc old, new;
- unsigned int dest;
- unsigned long flags;
-
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ if (vcpu->pre_pcpu == -1)
return;
- do {
- old.control = new.control = pi_desc->control;
-
- dest = cpu_physical_id(vcpu->cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
-
- /* Allow posting non-urgent interrupts */
- new.sn = 0;
-
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
-
- if(vcpu->pre_pcpu != -1) {
- spin_lock_irqsave(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
- }
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ __pi_post_block(vcpu);
+ local_irq_enable();
}
static void vmx_post_block(struct kvm_vcpu *vcpu)
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
- int idx, ret = -EINVAL;
+ int idx, ret = 0;
if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||
idx = srcu_read_lock(&kvm->irq_srcu);
irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+ if (guest_irq >= irq_rt->nr_rt_entries ||
+ hlist_empty(&irq_rt->map[guest_irq])) {
+ pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+ guest_irq, irq_rt->nr_rt_entries);
+ goto out;
+ }
hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
if (e->type != KVM_IRQ_ROUTING_MSI)
if (set)
ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else {
- /* suppress notification event before unposting */
- pi_set_sn(vcpu_to_pi_desc(vcpu));
+ else
ret = irq_set_vcpu_affinity(host_irq, NULL);
- pi_clear_sn(vcpu_to_pi_desc(vcpu));
- }
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
- .get_pkru = vmx_get_pkru,
-
.tlb_flush = vmx_flush_tlb,
.run = vmx_vcpu_run,