KVM: Device assignment permission checks

Only allow KVM device assignment to attach to devices which:

 - Are not bridges
 - Have BAR resources (assume others are special devices)
 - The user has permissions to use

Assigning a bridge is a configuration error, it's not supported, and
typically doesn't result in the behavior the user is expecting anyway.
Devices without BAR resources are typically chipset components that
also don't have host drivers.  We don't want users to hold such devices
captive or cause system problems by fencing them off into an iommu
domain.  We determine "permission to use" by testing whether the user
has access to the PCI sysfs resource files.  By default a normal user
will not have access to these files, so it provides a good indication
that an administration agent has granted the user access to the device.

[Yang Bai: add missing #include]
[avi: fix comment style]

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Yang Bai <hamo.by@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

2 files changed, 79 insertions, 0 deletions

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index ee2c96b3ba5a..4df9af4f6132 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1154,6 +1154,10 @@ following flags are specified:
 The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
 isolation of the device.  Usages not specifying this flag are deprecated.
 
+Only PCI header type 0 devices with PCI BAR resources are supported by
+device assignment.  The user requesting this ioctl must have read/write
+access to the PCI sysfs resource files associated with the device.
+
 4.49 KVM_DEASSIGN_PCI_DEVICE
 
 Capability: KVM_CAP_DEVICE_DEASSIGNMENT
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index a251a28f79c7..758e3b36d4cf 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,
@@ -480,12 +482,73 @@ 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;
@@ -516,6 +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;