Merge remote-tracking branch 'kvm/linux-next'

4 files changed, 123 insertions, 29 deletions

diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 4d28a9ddbee0..a8d540398bbd 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -490,7 +490,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 	mutex_lock(&kvm->irq_lock);
 	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
-	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
 
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
@@ -500,7 +500,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
 	synchronize_srcu(&kvm->irq_srcu);
-	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
 #endif
 
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 3bcc9990adf7..cc30d01a56be 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -142,8 +142,8 @@ static int setup_routing_entry(struct kvm *kvm,
 			       struct kvm_kernel_irq_routing_entry *e,
 			       const struct kvm_irq_routing_entry *ue)
 {
-	int r = -EINVAL;
 	struct kvm_kernel_irq_routing_entry *ei;
+	int r;
 
 	/*
 	 * Do not allow GSI to be mapped to the same irqchip more than once.
@@ -153,20 +153,19 @@ static int setup_routing_entry(struct kvm *kvm,
 		if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
-			return r;
+			return -EINVAL;
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
 	r = kvm_set_routing_entry(kvm, e, ue);
 	if (r)
-		goto out;
+		return r;
 	if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
 		rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
 
 	hlist_add_head(&e->link, &rt->map[e->gsi]);
-	r = 0;
-out:
-	return r;
+
+	return 0;
 }
 
 void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 88257b311cb5..357e67cba32e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1019,8 +1019,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 		old_memslots = install_new_memslots(kvm, as_id, slots);
 
-		/* slot was deleted or moved, clear iommu mapping */
-		kvm_iommu_unmap_pages(kvm, &old);
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -1055,21 +1053,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_free_memslot(kvm, &old, &new);
 	kvfree(old_memslots);
-
-	/*
-	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
-	 * un-mapped and re-mapped if their base changes.  Since base change
-	 * unmapping is handled above with slot deletion, mapping alone is
-	 * needed here.  Anything else the iommu might care about for existing
-	 * slots (size changes, userspace addr changes and read-only flag
-	 * changes) is disallowed above, so any other attribute changes getting
-	 * here can be skipped.
-	 */
-	if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
-		r = kvm_iommu_map_pages(kvm, &new);
-		return r;
-	}
-
 	return 0;
 
 out_slots:
@@ -2366,7 +2349,7 @@ static int kvm_vcpu_fault(struct vm_fault *vmf)
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
 #endif
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
@@ -2935,6 +2918,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
 	case KVM_CAP_CHECK_EXTENSION_VM:
 		return 1;
+#ifdef CONFIG_KVM_MMIO
+	case KVM_CAP_COALESCED_MMIO:
+		return KVM_COALESCED_MMIO_PAGE_OFFSET;
+#endif
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
@@ -2984,7 +2971,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
 		break;
 	}
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	case KVM_REGISTER_COALESCED_MMIO: {
 		struct kvm_coalesced_mmio_zone zone;
 
@@ -3082,8 +3069,11 @@ static long kvm_vm_ioctl(struct file *filp,
 					   routing.nr * sizeof(*entries)))
 				goto out_free_irq_routing;
 		}
+		/* avoid races with KVM_CREATE_IRQCHIP on x86 */
+		mutex_lock(&kvm->lock);
 		r = kvm_set_irq_routing(kvm, entries, routing.nr,
 					routing.flags);
+		mutex_unlock(&kvm->lock);
 out_free_irq_routing:
 		vfree(entries);
 		break;
@@ -3176,7 +3166,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	r = kvm_coalesced_mmio_init(kvm);
 	if (r < 0) {
 		kvm_put_kvm(kvm);
@@ -3229,7 +3219,7 @@ static long kvm_dev_ioctl(struct file *filp,
 #ifdef CONFIG_X86
 		r += PAGE_SIZE;    /* pio data page */
 #endif
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d32f239eb471..37d9118fd84b 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -20,6 +20,10 @@
 #include <linux/vfio.h>
 #include "vfio.h"
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
 struct kvm_vfio_group {
 	struct list_head node;
 	struct vfio_group *vfio_group;
@@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
 	return ret > 0;
 }
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+	int (*fn)(struct vfio_group *);
+	int ret = -EINVAL;
+
+	fn = symbol_get(vfio_external_user_iommu_id);
+	if (!fn)
+		return ret;
+
+	ret = fn(vfio_group);
+
+	symbol_put(vfio_external_user_iommu_id);
+
+	return ret;
+}
+
+static struct iommu_group *kvm_vfio_group_get_iommu_group(
+		struct vfio_group *group)
+{
+	int group_id = kvm_vfio_external_user_iommu_id(group);
+
+	if (group_id < 0)
+		return NULL;
+
+	return iommu_group_get_by_id(group_id);
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+		struct vfio_group *vfio_group)
+{
+	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+
+	if (WARN_ON_ONCE(!grp))
+		return;
+
+	kvm_spapr_tce_release_iommu_group(kvm, grp);
+	iommu_group_put(grp);
+}
+#endif
+
 /*
  * Groups can use the same or different IOMMU domains.  If the same then
  * adding a new group may change the coherency of groups we've previously
@@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(vfio_group, NULL);
 
 		kvm_vfio_group_put_external_user(vfio_group);
@@ -218,6 +266,57 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		kvm_vfio_update_coherency(dev);
 
 		return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+		struct kvm_vfio_spapr_tce param;
+		struct kvm_vfio *kv = dev->private;
+		struct vfio_group *vfio_group;
+		struct kvm_vfio_group *kvg;
+		struct fd f;
+		struct iommu_group *grp;
+
+		if (copy_from_user(&param, (void __user *)arg,
+				sizeof(struct kvm_vfio_spapr_tce)))
+			return -EFAULT;
+
+		f = fdget(param.groupfd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		grp = kvm_vfio_group_get_iommu_group(vfio_group);
+		if (WARN_ON_ONCE(!grp)) {
+			kvm_vfio_group_put_external_user(vfio_group);
+			return -EIO;
+		}
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+					param.tablefd, grp);
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		iommu_group_put(grp);
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
 	}
 
 	return -ENXIO;
@@ -242,6 +341,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_VFIO_GROUP_ADD:
 		case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
 			return 0;
 		}
 
@@ -257,6 +359,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	struct kvm_vfio_group *kvg, *tmp;
 
 	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		list_del(&kvg->node);