Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Tools:
   - kvm_stat: do not show halt_wait_ns since it is not a cumulative statistic

  x86:
   - clean ups and fixes for bus lock vmexit and lazy allocation of rmaps
   - two fixes for SEV-ES (one more coming as soon as I get reviews)
   - fix for static_key underflow

  ARM:
   - Properly refcount pages used as a concatenated stage-2 PGD
   - Fix missing unlock when detecting the use of MTE+VM_SHARED"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: SEV-ES: reduce ghcb_sa_len to 32 bits
  KVM: VMX: Remove redundant handling of bus lock vmexit
  KVM: kvm_stat: do not show halt_wait_ns
  KVM: x86: WARN if APIC HW/SW disable static keys are non-zero on unload
  Revert "KVM: x86: Open code necessary bits of kvm_lapic_set_base() at vCPU RESET"
  KVM: SEV-ES: Set guest_state_protected after VMSA update
  KVM: X86: fix lazy allocation of rmaps
  KVM: SEV-ES: fix length of string I/O
  KVM: arm64: Release mmap_lock when using VM_SHARED with MTE
  KVM: arm64: Report corrupted refcount at EL2
  KVM: arm64: Fix host stage-2 PGD refcount
  KVM: s390: Function documentation fixes

5 files changed, 32 insertions, 17 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 76fb00921203..d6ac32f3f650 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 msr_val;
 	int i;
 
 	if (!init_event) {
-		vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE |
-				       MSR_IA32_APICBASE_ENABLE;
+		msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 		if (kvm_vcpu_is_reset_bsp(vcpu))
-			vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+			msr_val |= MSR_IA32_APICBASE_BSP;
+		kvm_lapic_set_base(vcpu, msr_val);
 	}
 
 	if (!apic)
@@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	if (!init_event) {
-		apic->base_address = APIC_DEFAULT_PHYS_BASE;
-
+	/* The xAPIC ID is set at RESET even if the APIC was already enabled. */
+	if (!init_event)
 		kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
-	}
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
@@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 		lapic_timer_advance_dynamic = false;
 	}
 
+	/*
+	 * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
+	 * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset().
+	 */
+	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
 	static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
@@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 void kvm_lapic_exit(void)
 {
 	static_key_deferred_flush(&apic_hw_disabled);
+	WARN_ON(static_branch_unlikely(&apic_hw_disabled.key));
 	static_key_deferred_flush(&apic_sw_disabled);
+	WARN_ON(static_branch_unlikely(&apic_sw_disabled.key));
 }
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c36b5fe4c27c..0d21d59936e5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -618,7 +618,12 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
 	vmsa.address = __sme_pa(svm->vmsa);
 	vmsa.len = PAGE_SIZE;
-	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+	if (ret)
+	  return ret;
+
+	vcpu->arch.guest_state_protected = true;
+	return 0;
 }
 
 static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
@@ -2583,7 +2588,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 		return -EINVAL;
 
 	return kvm_sev_es_string_io(&svm->vcpu, size, port,
-				    svm->ghcb_sa, svm->ghcb_sa_len, in);
+				    svm->ghcb_sa, svm->ghcb_sa_len / size, in);
 }
 
 void sev_es_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 128a54b1fbf1..5d30db599e10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -191,7 +191,7 @@ struct vcpu_svm {
 
 	/* SEV-ES scratch area support */
 	void *ghcb_sa;
-	u64 ghcb_sa_len;
+	u32 ghcb_sa_len;
 	bool ghcb_sa_sync;
 	bool ghcb_sa_free;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 116b08904ac3..7fb2a3a1ca46 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5562,9 +5562,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 
 static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
 {
-	vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
-	vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
-	return 0;
+	/*
+	 * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK
+	 * VM-Exits. Unconditionally set the flag here and leave the handling to
+	 * vmx_handle_exit().
+	 */
+	to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+	return 1;
 }
 
 /*
@@ -6051,9 +6055,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	int ret = __vmx_handle_exit(vcpu, exit_fastpath);
 
 	/*
-	 * Even when current exit reason is handled by KVM internally, we
-	 * still need to exit to user space when bus lock detected to inform
-	 * that there is a bus lock in guest.
+	 * Exit to user space when bus lock detected to inform that there is
+	 * a bus lock in guest.
 	 */
 	if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
 		if (ret > 0)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index aabd3a2ec1bc..0c8b5129effd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11392,7 +11392,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
 		int level = i + 1;
 		int lpages = __kvm_mmu_slot_lpages(slot, npages, level);
 
-		WARN_ON(slot->arch.rmap[i]);
+		if (slot->arch.rmap[i])
+			continue;
 
 		slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.rmap[i]) {