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

Pull KVM fixes from Radim Krčmář:
 "KVM:
   - lock kvm_device list to prevent corruption on device creation.

  PPC:
   - split debugfs initialization from creation of the xics device to
     unlock the newly taken kvm lock earlier.

  s390:
   - prevent userspace from triggering two WARN_ON_ONCE.

  MIPS:
   - fix several issues in the management of TLB faults (Cc: stable)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  MIPS: KVM: Propagate kseg0/mapped tlb fault errors
  MIPS: KVM: Fix gfn range check in kseg0 tlb faults
  MIPS: KVM: Add missing gfn range check
  MIPS: KVM: Fix mapped fault broken commpage handling
  KVM: Protect device ops->create and list_add with kvm->lock
  KVM: PPC: Move xics_debugfs_init out of create
  KVM: s390: reset KVM_REQ_MMU_RELOAD if mapping the prefix failed
  KVM: s390: set the prefix initially properly

arch/arm/kvm/arm.c

@@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
+		int ret;
 		if (!vgic_present)
 			return -ENXIO;
-		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_lock(&kvm->lock);
+		ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_unlock(&kvm->lock);
+		return ret;
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
 		struct kvm_arm_device_addr dev_addr;

arch/mips/kvm/emulate.c

@@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
 
 	preempt_disable();
 	if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
-		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
+		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
-			kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+		    kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+			kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+				__func__, va, vcpu, read_c0_entryhi());
+			er = EMULATE_FAIL;
+			preempt_enable();
+			goto done;
+		}
 	} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
 		   KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
 		int index;
@@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
 								run, vcpu);
 				preempt_enable();
 				goto dont_update_pc;
-			} else {
+			}
-				/*
+			/*
-				 * We fault an entry from the guest tlb to the
+			 * We fault an entry from the guest tlb to the
-				 * shadow host TLB
+			 * shadow host TLB
-				 */
+			 */
-				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+				preempt_enable();
+				goto done;
 			}
 		}
 	} else {
@@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause,
 			 * OK we have a Guest TLB entry, now inject it into the
 			 * shadow host TLB
 			 */
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+			}
 		}
 	}
 

arch/mips/kvm/mmu.c

@@ -99,7 +99,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	}
 
 	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
-	if (gfn >= kvm->arch.guest_pmap_npages) {
+	if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
 		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
 			gfn, badvaddr);
 		kvm_mips_dump_host_tlbs();
@@ -138,35 +138,49 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
 	struct kvm *kvm = vcpu->kvm;
 	kvm_pfn_t pfn0, pfn1;
+	gfn_t gfn0, gfn1;
+	long tlb_lo[2];
 	int ret;
 
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
+	tlb_lo[0] = tlb->tlb_lo[0];
-		pfn0 = 0;
+	tlb_lo[1] = tlb->tlb_lo[1];
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0])
-					   >> PAGE_SHIFT) < 0)
-			return -1;
 
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1])
+	/*
-					   >> PAGE_SHIFT) < 0)
+	 * The commpage address must not be mapped to anything else if the guest
-			return -1;
+	 * TLB contains entries nearby, or commpage accesses will break.
+	 */
+	if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+			VPN2_MASK & (PAGE_MASK << 1)))
+		tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
 
-		pfn0 = kvm->arch.guest_pmap[
+	gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
-			mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT];
+	gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
-		pfn1 = kvm->arch.guest_pmap[
+	if (gfn0 >= kvm->arch.guest_pmap_npages ||
-			mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT];
+	    gfn1 >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+			__func__, gfn0, gfn1, tlb->tlb_hi);
+		kvm_mips_dump_guest_tlbs(vcpu);
+		return -1;
 	}
 
+	if (kvm_mips_map_page(kvm, gfn0) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(kvm, gfn1) < 0)
+		return -1;
+
+	pfn0 = kvm->arch.guest_pmap[gfn0];
+	pfn1 = kvm->arch.guest_pmap[gfn1];
+
 	/* Get attributes from the Guest TLB */
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
 		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
-		(tlb->tlb_lo[0] & ENTRYLO_D) |
+		(tlb_lo[0] & ENTRYLO_D) |
-		(tlb->tlb_lo[0] & ENTRYLO_V);
+		(tlb_lo[0] & ENTRYLO_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
 		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
-		(tlb->tlb_lo[1] & ENTRYLO_D) |
+		(tlb_lo[1] & ENTRYLO_D) |
-		(tlb->tlb_lo[1] & ENTRYLO_V);
+		(tlb_lo[1] & ENTRYLO_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo[0], tlb->tlb_lo[1]);
@@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu)
 				local_irq_restore(flags);
 				return KVM_INVALID_INST;
 			}
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
-							     &vcpu->arch.
+						&vcpu->arch.guest_tlb[index])) {
-							     guest_tlb[index]);
+				kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, index, vcpu,
+					read_c0_entryhi());
+				kvm_mips_dump_guest_tlbs(vcpu);
+				local_irq_restore(flags);
+				return KVM_INVALID_INST;
+			}
 			inst = *(opc);
 		}
 		local_irq_restore(flags);

arch/powerpc/kvm/book3s_xics.c

@@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 	xics->kvm = kvm;
 
 	/* Already there ? */
-	mutex_lock(&kvm->lock);
 	if (kvm->arch.xics)
 		ret = -EEXIST;
 	else
 		kvm->arch.xics = xics;
-	mutex_unlock(&kvm->lock);
 
 	if (ret) {
 		kfree(xics);
 		return ret;
 	}
 
-	xics_debugfs_init(xics);
-
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
 		/* Enable real mode support */
@@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
+static void kvmppc_xics_init(struct kvm_device *dev)
+{
+	struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;
+
+	xics_debugfs_init(xics);
+}
+
 struct kvm_device_ops kvm_xics_ops = {
 	.name = "kvm-xics",
 	.create = kvmppc_xics_create,
+	.init = kvmppc_xics_init,
 	.destroy = kvmppc_xics_free,
 	.set_attr = xics_set_attr,
 	.get_attr = xics_get_attr,

arch/s390/kvm/kvm-s390.c

@@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2361,8 +2362,10 @@ retry:
 		rc = gmap_mprotect_notify(vcpu->arch.gmap,
 					  kvm_s390_get_prefix(vcpu),
 					  PAGE_SIZE * 2, PROT_WRITE);
-		if (rc)
+		if (rc) {
+			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 			return rc;
+		}
 		goto retry;
 	}
 

include/linux/kvm_host.h

@@ -1113,8 +1113,20 @@ struct kvm_device {
 /* create, destroy, and name are mandatory */
 struct kvm_device_ops {
 	const char *name;
+
+	/*
+	 * create is called holding kvm->lock and any operations not suitable
+	 * to do while holding the lock should be deferred to init (see
+	 * below).
+	 */
 	int (*create)(struct kvm_device *dev, u32 type);
 
+	/*
+	 * init is called after create if create is successful and is called
+	 * outside of holding kvm->lock.
+	 */
+	void (*init)(struct kvm_device *dev);
+
 	/*
 	 * Destroy is responsible for freeing dev.
 	 *

virt/kvm/arm/vgic/vgic-init.c

@@ -73,12 +73,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	int i, vcpu_lock_idx = -1, ret;
 	struct kvm_vcpu *vcpu;
 
-	mutex_lock(&kvm->lock);
+	if (irqchip_in_kernel(kvm))
-
+		return -EEXIST;
-	if (irqchip_in_kernel(kvm)) {
-		ret = -EEXIST;
-		goto out;
-	}
 
 	/*
 	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
@@ -87,10 +83,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	 * the proper checks already.
 	 */
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
-		!kvm_vgic_global_state.can_emulate_gicv2) {
+		!kvm_vgic_global_state.can_emulate_gicv2)
-		ret = -ENODEV;
+		return -ENODEV;
-		goto out;
-	}
 
 	/*
 	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
@@ -138,9 +132,6 @@ out_unlock:
 		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
 		mutex_unlock(&vcpu->mutex);
 	}
-
-out:
-	mutex_unlock(&kvm->lock);
 	return ret;
 }
 

virt/kvm/kvm_main.c

@@ -696,6 +696,11 @@ static void kvm_destroy_devices(struct kvm *kvm)
 {
 	struct kvm_device *dev, *tmp;
 
+	/*
+	 * We do not need to take the kvm->lock here, because nobody else
+	 * has a reference to the struct kvm at this point and therefore
+	 * cannot access the devices list anyhow.
+	 */
 	list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
 		list_del(&dev->vm_node);
 		dev->ops->destroy(dev);
@@ -2832,19 +2837,28 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	dev->ops = ops;
 	dev->kvm = kvm;
 
+	mutex_lock(&kvm->lock);
 	ret = ops->create(dev, cd->type);
 	if (ret < 0) {
+		mutex_unlock(&kvm->lock);
 		kfree(dev);
 		return ret;
 	}
+	list_add(&dev->vm_node, &kvm->devices);
+	mutex_unlock(&kvm->lock);
+
+	if (ops->init)
+		ops->init(dev);
 
 	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
 	if (ret < 0) {
 		ops->destroy(dev);
+		mutex_lock(&kvm->lock);
+		list_del(&dev->vm_node);
+		mutex_unlock(&kvm->lock);
 		return ret;
 	}
 
-	list_add(&dev->vm_node, &kvm->devices);
 	kvm_get_kvm(kvm);
 	cd->fd = ret;
 	return 0;