KVM: x86: Move "KVM no-APIC vCPU" key management into local APIC code
Move incrementing and decrementing of kvm_has_noapic_vcpu into
kvm_create_lapic() and kvm_free_lapic() respectively to fix a benign bug
where KVM fails to decrement the count if vCPU creation ultimately fails,
e.g. due to a memory allocation failing.
Note, the bug is benign as kvm_has_noapic_vcpu is used purely to optimize
lapic_in_kernel() checks, and that optimization is quite dubious. That,
and practically speaking no setup that cares at all about performance runs
with a userspace local APIC.
Reported-by: Li RongQing <lirongqing@baidu.com>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Xu Yilun <yilun.xu@linux.intel.com>
Link: https://lore.kernel.org/r/20240209222047.394389-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3242f3d..681f6d8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -124,6 +124,9 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
+__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu);
+EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu);
+
__read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_hw_disabled, HZ);
__read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_sw_disabled, HZ);
@@ -2466,8 +2469,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!vcpu->arch.apic)
+ if (!vcpu->arch.apic) {
+ static_branch_dec(&kvm_has_noapic_vcpu);
return;
+ }
hrtimer_cancel(&apic->lapic_timer.timer);
@@ -2809,6 +2814,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
ASSERT(vcpu != NULL);
+ if (!irqchip_in_kernel(vcpu->kvm)) {
+ static_branch_inc(&kvm_has_noapic_vcpu);
+ return 0;
+ }
+
apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT);
if (!apic)
goto nomem;
@@ -2844,6 +2854,21 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
+ /*
+ * Defer evaluating inhibits until the vCPU is first run, as this vCPU
+ * will not get notified of any changes until this vCPU is visible to
+ * other vCPUs (marked online and added to the set of vCPUs).
+ *
+ * Opportunistically mark APICv active as VMX in particularly is highly
+ * unlikely to have inhibits. Ignore the current per-VM APICv state so
+ * that vCPU creation is guaranteed to run with a deterministic value,
+ * the request will ensure the vCPU gets the correct state before VM-Entry.
+ */
+ if (enable_apicv) {
+ apic->apicv_active = true;
+ kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
+ }
+
return 0;
nomem_free_apic:
kfree(apic);
