[ 037/180] KVM: Device assignment permission checks

[Willy Tarreau]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Williamson <alex.williamson@xxxxxxxxxx>

commit 3d27e23b17010c668db311140b17bbbb70c78fb9 upstream

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@xxxxxxxxxx>
Signed-off-by: Yang Bai <hamo.by@xxxxxxxxx>
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
[dannf: backported to Debian's 2.6.32]
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 virt/kvm/kvm_main.c |   75 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 75 insertions(+), 0 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 77288e2..311ec18 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -43,6 +43,8 @@
 #include <linux/swap.h>
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -575,12 +577,73 @@ 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;
 	struct kvm_assigned_dev_kernel *match;
 	struct pci_dev *dev;
+	u8 header_type;
 
 	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
 		return -EINVAL;
@@ -610,6 +673,18 @@ 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;
-- 
1.7.2.1.45.g54fbc



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/