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 3242f3da2457671bafde8d5ad7823c9a3d3a07be..681f6d82d015070676dfc59b557c122bfc78560d 100644 (file)
--- 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);

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d9724a35d8f322ce5579d7228cbfcff71b073f96..19b18679779cd01b774f66d64a223b8af08616d1 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12046,27 +12046,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
        if (r < 0)
                return r;
 
-       if (irqchip_in_kernel(vcpu->kvm)) {
-               r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
-               if (r < 0)
-                       goto fail_mmu_destroy;
-
-               /*
-                * 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) {
-                       vcpu->arch.apic->apicv_active = true;
-                       kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
-               }
-       } else
-               static_branch_inc(&kvm_has_noapic_vcpu);
+       r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+       if (r < 0)
+               goto fail_mmu_destroy;
 
        r = -ENOMEM;
 
@@ -12187,8 +12169,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
        srcu_read_unlock(&vcpu->kvm->srcu, idx);
        free_page((unsigned long)vcpu->arch.pio_data);
        kvfree(vcpu->arch.cpuid_entries);
-       if (!lapic_in_kernel(vcpu))
-               static_branch_dec(&kvm_has_noapic_vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -12465,9 +12445,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
        return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
 }
 
-__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu);
-EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu);
-
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
        struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);