1 files changed, 120 insertions, 39 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 6cc4b97..758e3b3 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
 #include "irq.h"
 
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
@@ -58,8 +60,6 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
 static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-	u32 vector;
-	int index;
 
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_INTX) {
 		spin_lock(&assigned_dev->intx_lock);
@@ -68,31 +68,35 @@ static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
 		spin_unlock(&assigned_dev->intx_lock);
 	}
 
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		index = find_index_from_host_irq(assigned_dev, irq);
-		if (index >= 0) {
-			vector = assigned_dev->
-					guest_msix_entries[index].vector;
-			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id, vector, 1);
-		}
-	} else
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+		    assigned_dev->guest_irq, 1);
+
+	return IRQ_HANDLED;
+}
+
+#ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int index = find_index_from_host_irq(assigned_dev, irq);
+	u32 vector;
+
+	if (index >= 0) {
+		vector = assigned_dev->guest_msix_entries[index].vector;
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-			    assigned_dev->guest_irq, 1);
+			    vector, 1);
+	}
 
 	return IRQ_HANDLED;
 }
+#endif
 
 /* Ack the irq line for an assigned device */
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
-	struct kvm_assigned_dev_kernel *dev;
-
-	if (kian->gsi == -1)
-		return;
-
-	dev = container_of(kian, struct kvm_assigned_dev_kernel,
-			   ack_notifier);
+	struct kvm_assigned_dev_kernel *dev =
+		container_of(kian, struct kvm_assigned_dev_kernel,
+			     ack_notifier);
 
 	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
 
@@ -110,8 +114,9 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 static void deassign_guest_irq(struct kvm *kvm,
 			       struct kvm_assigned_dev_kernel *assigned_dev)
 {
-	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
-	assigned_dev->ack_notifier.gsi = -1;
+	if (assigned_dev->ack_notifier.gsi != -1)
+		kvm_unregister_irq_ack_notifier(kvm,
+						&assigned_dev->ack_notifier);
 
 	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
 		    assigned_dev->guest_irq, 0);
@@ -143,7 +148,7 @@ static void deassign_host_irq(struct kvm *kvm,
 
 		for (i = 0; i < assigned_dev->entries_nr; i++)
 			free_irq(assigned_dev->host_msix_entries[i].vector,
-				 (void *)assigned_dev);
+				 assigned_dev);
 
 		assigned_dev->entries_nr = 0;
 		kfree(assigned_dev->host_msix_entries);
@@ -153,7 +158,7 @@ static void deassign_host_irq(struct kvm *kvm,
 		/* Deal with MSI and INTx */
 		disable_irq(assigned_dev->host_irq);
 
-		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+		free_irq(assigned_dev->host_irq, assigned_dev);
 
 		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
 			pci_disable_msi(assigned_dev->dev);
@@ -205,6 +210,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 	else
 		pci_restore_state(assigned_dev->dev);
 
+	assigned_dev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+
 	pci_release_regions(assigned_dev->dev);
 	pci_disable_device(assigned_dev->dev);
 	pci_dev_put(assigned_dev->dev);
@@ -237,7 +244,7 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 	 * are going to be long delays in accepting, acking, etc.
 	 */
 	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 IRQF_ONESHOT, dev->irq_name, (void *)dev))
+				 IRQF_ONESHOT, dev->irq_name, dev))
 		return -EIO;
 	return 0;
 }
@@ -256,7 +263,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 
 	dev->host_irq = dev->dev->irq;
 	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 0, dev->irq_name, (void *)dev)) {
+				 0, dev->irq_name, dev)) {
 		pci_disable_msi(dev->dev);
 		return -EIO;
 	}
@@ -282,8 +289,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 
 	for (i = 0; i < dev->entries_nr; i++) {
 		r = request_threaded_irq(dev->host_msix_entries[i].vector,
-					 NULL, kvm_assigned_dev_thread,
-					 0, dev->irq_name, (void *)dev);
+					 NULL, kvm_assigned_dev_thread_msix,
+					 0, dev->irq_name, dev);
 		if (r)
 			goto err;
 	}
@@ -291,7 +298,7 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 	return 0;
 err:
 	for (i -= 1; i >= 0; i--)
-		free_irq(dev->host_msix_entries[i].vector, (void *)dev);
+		free_irq(dev->host_msix_entries[i].vector, dev);
 	pci_disable_msix(dev->dev);
 	return r;
 }
@@ -404,7 +411,8 @@ static int assign_guest_irq(struct kvm *kvm,
 
 	if (!r) {
 		dev->irq_requested_type |= guest_irq_type;
-		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+		if (dev->ack_notifier.gsi != -1)
+			kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
 	} else
 		kvm_free_irq_source_id(kvm, dev->irq_source_id);
 
@@ -474,12 +482,76 @@ out:
 	return r;
 }
 
+/*
+ * We want to test whether the caller has been granted permissions to
+ * use this device.  To be able to configure and control the device,
+ * the user needs access to PCI configuration space and BAR resources.
+ * These are accessed through PCI sysfs.  PCI config space is often
+ * passed to the process calling this ioctl via file descriptor, so we
+ * can't rely on access to that file.  We can check for permissions
+ * on each of the BAR resource files, which is a pretty clear
+ * indicator that the user has been granted access to the device.
+ */
+static int probe_sysfs_permissions(struct pci_dev *dev)
+{
+#ifdef CONFIG_SYSFS
+	int i;
+	bool bar_found = false;
+
+	for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
+		char *kpath, *syspath;
+		struct path path;
+		struct inode *inode;
+		int r;
+
+		if (!pci_resource_len(dev, i))
+			continue;
+
+		kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
+		if (!kpath)
+			return -ENOMEM;
+
+		/* Per sysfs-rules, sysfs is always at /sys */
+		syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
+		kfree(kpath);
+		if (!syspath)
+			return -ENOMEM;
+
+		r = kern_path(syspath, LOOKUP_FOLLOW, &path);
+		kfree(syspath);
+		if (r)
+			return r;
+
+		inode = path.dentry->d_inode;
+
+		r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
+		path_put(&path);
+		if (r)
+			return r;
+
+		bar_found = true;
+	}
+
+	/* If no resources, probably something special */
+	if (!bar_found)
+		return -EPERM;
+
+	return 0;
+#else
+	return -EINVAL; /* No way to control the device without sysfs */
+#endif
+}
+
 static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 				      struct kvm_assigned_pci_dev *assigned_dev)
 {
 	int r = 0, idx;
 	struct kvm_assigned_dev_kernel *match;
 	struct pci_dev *dev;
+	u8 header_type;
+
+	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
+		return -EINVAL;
 
 	mutex_lock(&kvm->lock);
 	idx = srcu_read_lock(&kvm->srcu);
@@ -507,6 +579,18 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 		r = -EINVAL;
 		goto out_free;
 	}
+
+	/* Don't allow bridges to be assigned */
+	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+	if ((header_type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) {
+		r = -EPERM;
+		goto out_put;
+	}
+
+	r = probe_sysfs_permissions(dev);
+	if (r)
+		goto out_put;
+
 	if (pci_enable_device(dev)) {
 		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
 		r = -EBUSY;
@@ -538,16 +622,14 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
-	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
-		if (!kvm->arch.iommu_domain) {
-			r = kvm_iommu_map_guest(kvm);
-			if (r)
-				goto out_list_del;
-		}
-		r = kvm_assign_device(kvm, match);
+	if (!kvm->arch.iommu_domain) {
+		r = kvm_iommu_map_guest(kvm);
 		if (r)
 			goto out_list_del;
 	}
+	r = kvm_assign_device(kvm, match);
+	if (r)
+		goto out_list_del;
 
 out:
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -587,8 +669,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
 		goto out;
 	}
 
-	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
-		kvm_deassign_device(kvm, match);
+	kvm_deassign_device(kvm, match);
 
 	kvm_free_assigned_device(kvm, match);
 
@@ -617,7 +698,7 @@ static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
 	if (adev->entries_nr == 0) {
 		adev->entries_nr = entry_nr->entry_nr;
 		if (adev->entries_nr == 0 ||
-		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+		    adev->entries_nr > KVM_MAX_MSIX_PER_DEV) {
 			r = -EINVAL;
 			goto msix_nr_out;
 		}