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

11 files changed, 79 insertions, 21 deletions

diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fb0f523d1492..0a048dc06a7d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -24,6 +24,7 @@ struct hyp_pool {
 
 /* Allocation */
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
 void hyp_get_page(struct hyp_pool *pool, void *addr);
 void hyp_put_page(struct hyp_pool *pool, void *addr);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..34eeb524b686 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
 
 static void *host_s2_zalloc_pages_exact(size_t size)
 {
-	return hyp_alloc_pages(&host_s2_pool, get_order(size));
+	void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+	hyp_split_page(hyp_virt_to_page(addr));
+
+	/*
+	 * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+	 * so there should be no need to free any of the tail pages to make the
+	 * allocation exact.
+	 */
+	WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+	return addr;
 }
 
 static void *host_s2_zalloc_page(void *pool)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 41fc25bdfb34..0bd7701ad1df 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
 
 static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
 {
+	BUG_ON(!p->refcount);
 	p->refcount--;
 	return (p->refcount == 0);
 }
@@ -193,6 +194,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
 	hyp_spin_unlock(&pool->lock);
 }
 
+void hyp_split_page(struct hyp_page *p)
+{
+	unsigned short order = p->order;
+	unsigned int i;
+
+	p->order = 0;
+	for (i = 1; i < (1 << order); i++) {
+		struct hyp_page *tail = p + i;
+
+		tail->order = 0;
+		hyp_set_page_refcounted(tail);
+	}
+}
+
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
 {
 	unsigned short i = order;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1a94a7ca48f2..69bd1732a299 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		 * when updating the PG_mte_tagged page flag, see
 		 * sanitise_mte_tags for more details.
 		 */
-		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
-			return -EINVAL;
+		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) {
+			ret = -EINVAL;
+			break;
+		}
 
 		if (vma->vm_flags & VM_PFNMAP) {
 			/* IO region dirty page logging not allowed */
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index b9f85b2dc053..6af59c59cc1b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 
 /**
  * guest_translate_address - translate guest logical into guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @gpa: Guest physical address
+ * @mode: Translation access mode
  *
  * Parameter semantics are the same as the ones from guest_translate.
  * The memory contents at the guest address are not changed.
@@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * check_gva_range - test a range of guest virtual addresses for accessibility
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @length: Length of test range
+ * @mode: Translation access mode
  */
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
@@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @vcpu: virtual cpu
  * @gra: Guest real address
  *
  * Checks whether an address is subject to low-address protection and set
@@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
  * @pgt: pointer to the beginning of the page table for the given address if
  *	 successful (return value 0), or to the first invalid DAT entry in
  *	 case of exceptions (return value > 0)
+ * @dat_protection: referenced memory is write protected
  * @fake: pgt references contiguous guest memory block, not a pgtable
  */
 static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 72b25b7cc6ae..2bd8f854f1b4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 
 /**
  * handle_external_interrupt - used for external interruption interceptions
+ * @vcpu: virtual cpu
  *
  * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
  * the new PSW does not have external interrupts disabled. In the first case,
@@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 }
 
 /**
- * Handle MOVE PAGE partial execution interception.
+ * handle_mvpg_pei - Handle MOVE PAGE partial execution interception.
+ * @vcpu: virtual cpu
  *
  * This interception can only happen for guests with DAT disabled and
  * addresses that are currently not mapped in the host. Thus we try to
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]) {