[PATCH] vfio: Lock down no-IOMMU mode when kernel is locked down

[Maxime Coquelin]

When no-IOMMU mode is enabled, VFIO is as unsafe as accessing
the PCI BARs via the device's sysfs, which is locked down when
the kernel is locked down.

Indeed, it is possible for an attacker to craft DMA requests
to modify kernel's code or leak secrets stored in the kernel,
since the device is not isolated by an IOMMU.

This patch introduces a new integrity lockdown reason for the
unsafe VFIO no-iommu mode.

Signed-off-by: Maxime Coquelin <maxime.coquelin@xxxxxxxxxx>
---
 drivers/vfio/vfio.c      | 13 +++++++++----
 include/linux/security.h |  1 +
 security/security.c      |  1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 5e631c359ef2..fe466d6ea5d8 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -25,6 +25,7 @@
 #include <linux/pci.h>
 #include <linux/rwsem.h>
 #include <linux/sched.h>
+#include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/string.h>
@@ -165,7 +166,8 @@ static void *vfio_noiommu_open(unsigned long arg)
 {
 	if (arg != VFIO_NOIOMMU_IOMMU)
 		return ERR_PTR(-EINVAL);
-	if (!capable(CAP_SYS_RAWIO))
+	if (!capable(CAP_SYS_RAWIO) ||
+			security_locked_down(LOCKDOWN_VFIO_NOIOMMU))
 		return ERR_PTR(-EPERM);
 
 	return NULL;
@@ -1280,7 +1282,8 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	if (atomic_read(&group->container_users))
 		return -EINVAL;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO))
+	if (group->noiommu && (!capable(CAP_SYS_RAWIO) ||
+			security_locked_down(LOCKDOWN_VFIO_NOIOMMU)))
 		return -EPERM;
 
 	f = fdget(container_fd);
@@ -1362,7 +1365,8 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	    !group->container->iommu_driver || !vfio_group_viable(group))
 		return -EINVAL;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO))
+	if (group->noiommu && (!capable(CAP_SYS_RAWIO) ||
+			security_locked_down(LOCKDOWN_VFIO_NOIOMMU)))
 		return -EPERM;
 
 	device = vfio_device_get_from_name(group, buf);
@@ -1490,7 +1494,8 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 	if (!group)
 		return -ENODEV;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO)) {
+	if (group->noiommu && (!capable(CAP_SYS_RAWIO) ||
+			security_locked_down(LOCKDOWN_VFIO_NOIOMMU))) {
 		vfio_group_put(group);
 		return -EPERM;
 	}
diff --git a/include/linux/security.h b/include/linux/security.h
index 06f7c50ce77f..f29388180fab 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -120,6 +120,7 @@ enum lockdown_reason {
 	LOCKDOWN_MMIOTRACE,
 	LOCKDOWN_DEBUGFS,
 	LOCKDOWN_XMON_WR,
+	LOCKDOWN_VFIO_NOIOMMU,
 	LOCKDOWN_INTEGRITY_MAX,
 	LOCKDOWN_KCORE,
 	LOCKDOWN_KPROBES,
diff --git a/security/security.c b/security/security.c
index b38155b2de83..33c3ddb6dcab 100644
--- a/security/security.c
+++ b/security/security.c
@@ -58,6 +58,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = {
 	[LOCKDOWN_MMIOTRACE] = "unsafe mmio",
 	[LOCKDOWN_DEBUGFS] = "debugfs access",
 	[LOCKDOWN_XMON_WR] = "xmon write access",
+	[LOCKDOWN_VFIO_NOIOMMU] = "VFIO unsafe no-iommu mode",
 	[LOCKDOWN_INTEGRITY_MAX] = "integrity",
 	[LOCKDOWN_KCORE] = "/proc/kcore access",
 	[LOCKDOWN_KPROBES] = "use of kprobes",
-- 
2.31.1