roots_to_free |= KVM_MMU_ROOT_CURRENT;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
- if (is_obsolete_root(kvm, mmu->root.hpa))
+ if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa))
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
}
uint i;
if (pcid == kvm_get_active_pcid(vcpu)) {
- mmu->invlpg(vcpu, gva, mmu->root.hpa);
+ if (mmu->invlpg)
+ mmu->invlpg(vcpu, gva, mmu->root.hpa);
tlb_flush = true;
}
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
if (VALID_PAGE(mmu->prev_roots[i].hpa) &&
pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) {
- mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);
+ if (mmu->invlpg)
+ mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);
tlb_flush = true;
}
}
{
struct kvm_mmu_page *sp, *node;
int nr_zapped, batch = 0;
+ bool unstable;
restart:
list_for_each_entry_safe_reverse(sp, node,
goto restart;
}
- if (__kvm_mmu_prepare_zap_page(kvm, sp,
- &kvm->arch.zapped_obsolete_pages, &nr_zapped)) {
- batch += nr_zapped;
+ unstable = __kvm_mmu_prepare_zap_page(kvm, sp,
+ &kvm->arch.zapped_obsolete_pages, &nr_zapped);
+ batch += nr_zapped;
+
+ if (unstable)
goto restart;
- }
}
/*
return 1;
}
+void __svm_write_tsc_multiplier(u64 multiplier)
+{
+ preempt_disable();
+
+ if (multiplier == __this_cpu_read(current_tsc_ratio))
+ goto out;
+
+ wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+ __this_cpu_write(current_tsc_ratio, multiplier);
+out:
+ preempt_enable();
+}
+
static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (tsc_scaling)
- wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
+ __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
cpu_svm_disable();
* Set the default value, even if we don't use TSC scaling
* to avoid having stale value in the msr
*/
- wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
- __this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT);
+ __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
}
vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
}
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
{
- wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+ __svm_write_tsc_multiplier(multiplier);
}
+
/* Evaluate instruction intercepts that depend on guest CPUID features. */
static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
struct vcpu_svm *svm)
*/
vmsave(__sme_page_pa(sd->save_area));
if (sev_es_guest(vcpu->kvm)) {
- struct vmcb_save_area *hostsa;
- hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
+ struct sev_es_save_area *hostsa;
+ hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
sev_es_prepare_switch_to_guest(hostsa);
}
- if (tsc_scaling) {
- u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
- if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
- __this_cpu_write(current_tsc_ratio, tsc_ratio);
- wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
- }
- }
+ if (tsc_scaling)
+ __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
if (likely(tsc_aux_uret_slot >= 0))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
"tr:",
save01->tr.selector, save01->tr.attrib,
save01->tr.limit, save01->tr.base);
- pr_err("cpl: %d efer: %016llx\n",
- save->cpl, save->efer);
+ pr_err("vmpl: %d cpl: %d efer: %016llx\n",
+ save->vmpl, save->cpl, save->efer);
pr_err("%-15s %016llx %-13s %016llx\n",
"cr0:", save->cr0, "cr2:", save->cr2);
pr_err("%-15s %016llx %-13s %016llx\n",
static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
{
+ if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR)
+ vcpu->arch.at_instruction_boundary = true;
}
static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
struct vcpu_sev_es_state {
/* SEV-ES support */
- struct vmcb_save_area *vmsa;
+ struct sev_es_save_area *vmsa;
struct ghcb *ghcb;
struct kvm_host_map ghcb_map;
bool received_first_sipi;
bool has_error_code, u32 error_code);
int nested_svm_exit_special(struct vcpu_svm *svm);
void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu);
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier);
+void __svm_write_tsc_multiplier(u64 multiplier);
void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
struct vmcb_control_area *control);
void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
void sev_es_init_vmcb(struct vcpu_svm *svm);
void sev_es_vcpu_reset(struct vcpu_svm *svm);
void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
- void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa);
+ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa);
void sev_es_unmap_ghcb(struct vcpu_svm *svm);
/* vmenter.S */
int size = PAGE_SIZE << L1D_CACHE_ORDER;
/*
- * This code is only executed when the the flush mode is 'cond' or
+ * This code is only executed when the flush mode is 'cond' or
* 'always'
*/
if (static_branch_likely(&vmx_l1d_flush_cond)) {
return;
handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+ vcpu->arch.at_instruction_boundary = true;
}
static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
STATS_DESC_COUNTER(VCPU, nested_run),
STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
STATS_DESC_COUNTER(VCPU, directed_yield_successful),
+ STATS_DESC_COUNTER(VCPU, preemption_reported),
+ STATS_DESC_COUNTER(VCPU, preemption_other),
STATS_DESC_ICOUNTER(VCPU, guest_mode)
};
struct kvm_memslots *slots;
static const u8 preempted = KVM_VCPU_PREEMPTED;
+ /*
+ * The vCPU can be marked preempted if and only if the VM-Exit was on
+ * an instruction boundary and will not trigger guest emulation of any
+ * kind (see vcpu_run). Vendor specific code controls (conservatively)
+ * when this is true, for example allowing the vCPU to be marked
+ * preempted if and only if the VM-Exit was due to a host interrupt.
+ */
+ if (!vcpu->arch.at_instruction_boundary) {
+ vcpu->stat.preemption_other++;
+ return;
+ }
+
+ vcpu->stat.preemption_reported++;
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
{
int idx;
- if (vcpu->preempted && !vcpu->arch.guest_state_protected)
- vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+ if (vcpu->preempted) {
+ if (!vcpu->arch.guest_state_protected)
+ vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
- /*
- * Take the srcu lock as memslots will be accessed to check the gfn
- * cache generation against the memslots generation.
- */
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (kvm_xen_msr_enabled(vcpu->kvm))
- kvm_xen_runstate_set_preempted(vcpu);
- else
- kvm_steal_time_set_preempted(vcpu);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ /*
+ * Take the srcu lock as memslots will be accessed to check the gfn
+ * cache generation against the memslots generation.
+ */
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ if (kvm_xen_msr_enabled(vcpu->kvm))
+ kvm_xen_runstate_set_preempted(vcpu);
+ else
+ kvm_steal_time_set_preempted(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ }
static_call(kvm_x86_vcpu_put)(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
vcpu->arch.l1tf_flush_l1d = true;
for (;;) {
+ /*
+ * If another guest vCPU requests a PV TLB flush in the middle
+ * of instruction emulation, the rest of the emulation could
+ * use a stale page translation. Assume that any code after
+ * this point can start executing an instruction.
+ */
+ vcpu->arch.at_instruction_boundary = false;
if (kvm_vcpu_running(vcpu)) {
r = vcpu_enter_guest(vcpu);
} else {
if (current->mm == kvm->mm) {
/*
* Free memory regions allocated on behalf of userspace,
- * unless the the memory map has changed due to process exit
+ * unless the memory map has changed due to process exit
* or fd copying.
*/
mutex_lock(&kvm->slots_lock);
r = kvm_arch_prepare_memory_region(kvm, old, new, change);
/* Free the bitmap on failure if it was allocated above. */
- if (r && new && new->dirty_bitmap && old && !old->dirty_bitmap)
+ if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
kvm_destroy_dirty_bitmap(new);
return r;
kvm_put_kvm_no_destroy(kvm);
mutex_lock(&kvm->lock);
list_del(&dev->vm_node);
+ if (ops->release)
+ ops->release(dev);
mutex_unlock(&kvm->lock);
- ops->destroy(dev);
+ if (ops->destroy)
+ ops->destroy(dev);
return ret;
}