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

Pull KVM fixes from Paolo Bonzini:
 "Bug fixes (ARM, s390, x86)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: async_pf: avoid async pf injection when in guest mode
  KVM: cpuid: Fix read/write out-of-bounds vulnerability in cpuid emulation
  arm: KVM: Allow unaligned accesses at HYP
  arm64: KVM: Allow unaligned accesses at EL2
  arm64: KVM: Preserve RES1 bits in SCTLR_EL2
  KVM: arm/arm64: Handle possible NULL stage2 pud when ageing pages
  KVM: nVMX: Fix exception injection
  kvm: async_pf: fix rcu_irq_enter() with irqs enabled
  KVM: arm/arm64: vgic-v3: Fix nr_pre_bits bitfield extraction
  KVM: s390: fix ais handling vs cpu model
  KVM: arm/arm64: Fix isues with GICv2 on GICv3 migration

13 files changed, 40 insertions, 32 deletions

diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 570ed4a9c261..5386528665b5 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -104,7 +104,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -112,8 +111,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 15c142ce991c..b4d13d9267ff 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -286,6 +286,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 839425c24b1c..3f9615582377 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -106,10 +106,13 @@ __do_hyp_init:
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_ELx_FLAGS
-	orr	x4, x4, x5
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 79f37e37d367..6260b69e5622 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -65,8 +65,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
 		 * The vgic_set_vmcr() will convert to ICH_VMCR layout.
 		 */
-		vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
-		vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+		vmcr.cbpr = (val & ICC_CTLR_EL1_CBPR_MASK) >> ICC_CTLR_EL1_CBPR_SHIFT;
+		vmcr.eoim = (val & ICC_CTLR_EL1_EOImode_MASK) >> ICC_CTLR_EL1_EOImode_SHIFT;
 		vgic_set_vmcr(vcpu, &vmcr);
 	} else {
 		val = 0;
@@ -83,8 +83,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 		 * Extract it directly using ICC_CTLR_EL1 reg definitions.
 		 */
-		val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
-		val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+		val |= (vmcr.cbpr << ICC_CTLR_EL1_CBPR_SHIFT) & ICC_CTLR_EL1_CBPR_MASK;
+		val |= (vmcr.eoim << ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
 
 		p->regval = val;
 	}
@@ -135,7 +135,7 @@ static bool access_gic_bpr1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		p->regval = 0;
 
 	vgic_get_vmcr(vcpu, &vmcr);
-	if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+	if (!vmcr.cbpr) {
 		if (p->is_write) {
 			vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
 				     ICC_BPR1_EL1_SHIFT;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 426614a882a9..65d07ac34647 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -541,7 +541,6 @@ struct kvm_s390_float_interrupt {
 	struct mutex ais_lock;
 	u8 simm;
 	u8 nimm;
-	int ais_enabled;
 };
 
 struct kvm_hw_wp_info_arch {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index caf15c8a8948..2d120fef7d90 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2160,7 +2160,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_ais_req req;
 	int ret = 0;
 
-	if (!fi->ais_enabled)
+	if (!test_kvm_facility(kvm, 72))
 		return -ENOTSUPP;
 
 	if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
@@ -2204,7 +2204,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm,
 	};
 	int ret = 0;
 
-	if (!fi->ais_enabled || !adapter->suppressible)
+	if (!test_kvm_facility(kvm, 72) || !adapter->suppressible)
 		return kvm_s390_inject_vm(kvm, &s390int);
 
 	mutex_lock(&fi->ais_lock);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 689ac48361c6..f28e2e776931 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -558,7 +558,6 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		} else {
 			set_kvm_facility(kvm->arch.model.fac_mask, 72);
 			set_kvm_facility(kvm->arch.model.fac_list, 72);
-			kvm->arch.float_int.ais_enabled = 1;
 			r = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -1533,7 +1532,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.float_int.ais_lock);
 	kvm->arch.float_int.simm = 0;
 	kvm->arch.float_int.nimm = 0;
-	kvm->arch.float_int.ais_enabled = 0;
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
 		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index da5c09789984..43e10d6fdbed 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a181ae76c71c..59ca2eea522c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -780,18 +780,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5d3376f67794..cb8225969255 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3698,12 +3698,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3719,7 +3722,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 27975807cc64..330bf3a811fb 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9b4b5d6dcd34..ca5d2b93385c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2425,7 +2425,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2cd0997343c..87d3cb901935 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8607,8 +8607,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)