[PATCH v5 6/9] vfio/group: Add VFIO_CDEV_NOIOMMU Kconfig and tolerate NULL group

[Jacob Pan <jacob.pan@linux.microsoft.com>]

Add a new CONFIG_VFIO_CDEV_NOIOMMU option, independent of
CONFIG_VFIO_GROUP, to support noiommu mode via the cdev interface.

Since CONFIG_VFIO_GROUP can be enabled while CONFIG_VFIO_GROUP_NOIOMMU
is not, guard the noiommu group allocation in vfio_group_find_or_alloc()
with IS_ENABLED(CONFIG_VFIO_GROUP_NOIOMMU) to prevent creating spurious
/dev/vfio/noiommu-N group files when only cdev noiommu is configured.

For cdev noiommu devices that have no group, let vfio_device_set_group()
return success with a NULL group pointer and add null guards in group
functions that may be called during device lifecycle. These guards are
contained within group.c and are dead code for IOMMU-enabled devices
where device->group is always non-NULL.

Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
---
 drivers/vfio/Kconfig | 17 +++++++++++++++++
 drivers/vfio/group.c | 31 +++++++++++++++++++++++++++++--
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 39939be2908e..b1b1633412a9 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -75,6 +75,23 @@ config VFIO_GROUP_NOIOMMU
 
 	  If you don't know what to do here, say N.
 
+config VFIO_CDEV_NOIOMMU
+	bool "VFIO cdev No-IOMMU support"
+	depends on VFIO_DEVICE_CDEV
+	select IOMMUFD_NOIOMMU
+	help
+	  VFIO cdev no-IOMMU mode enables device access via the cdev
+	  interface without hardware IOMMU backing. This relies on
+	  IOMMUFD_NOIOMMU to provide a SW-only IO page table for
+	  IOVA-to-PA lookups.
+
+	  Use of this mode will result in an unsupportable kernel and
+	  will therefore taint the kernel. Device assignment to virtual
+	  machines is also not possible with this mode since there is
+	  no IOMMU to provide DMA translation.
+
+	  If you don't know what to do here, say N.
+
 config VFIO_VIRQFD
 	bool
 	select EVENTFD
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index 5b9329df04e5..c8a75ee28f20 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -386,6 +386,9 @@ int vfio_device_block_group(struct vfio_device *device)
 	struct vfio_group *group = device->group;
 	int ret = 0;
 
+	if (!group)
+		return 0;
+
 	mutex_lock(&group->group_lock);
 	if (group->opened_file) {
 		ret = -EBUSY;
@@ -403,6 +406,9 @@ void vfio_device_unblock_group(struct vfio_device *device)
 {
 	struct vfio_group *group = device->group;
 
+	if (!group)
+		return;
+
 	mutex_lock(&group->group_lock);
 	group->cdev_device_open_cnt--;
 	mutex_unlock(&group->group_lock);
@@ -641,7 +647,8 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
 	struct vfio_group *group;
 
 	iommu_group = iommu_group_get(dev);
-	if (!iommu_group && vfio_noiommu) {
+	if (!iommu_group && IS_ENABLED(CONFIG_VFIO_GROUP_NOIOMMU) &&
+	    vfio_noiommu) {
 		/*
 		 * With noiommu enabled, create an IOMMU group for devices that
 		 * don't already have one, implying no IOMMU hardware/driver
@@ -686,8 +693,19 @@ int vfio_device_set_group(struct vfio_device *device,
 	else
 		group = vfio_noiommu_group_alloc(device->dev, type);
 
-	if (IS_ERR(group))
+	if (IS_ERR(group)) {
+		/*
+		 * Cdev noiommu devices don't need a vfio_group. When
+		 * CONFIG_VFIO_GROUP_NOIOMMU is not set, the group alloc
+		 * above returns -EINVAL for devices without an IOMMU.
+		 * That's fine — a NULL group is expected and iommufd
+		 * handles these devices directly.
+		 */
+		if (IS_ENABLED(CONFIG_VFIO_CDEV_NOIOMMU) &&
+		    vfio_noiommu && !device->dev->iommu)
+			return 0;
 		return PTR_ERR(group);
+	}
 
 	/* Our reference on group is moved to the device */
 	device->group = group;
@@ -699,6 +717,9 @@ void vfio_device_remove_group(struct vfio_device *device)
 	struct vfio_group *group = device->group;
 	struct iommu_group *iommu_group;
 
+	if (!group)
+		return;
+
 	if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
 		iommu_group_remove_device(device->dev);
 
@@ -742,6 +763,8 @@ void vfio_device_remove_group(struct vfio_device *device)
 
 void vfio_device_group_register(struct vfio_device *device)
 {
+	if (!device->group)
+		return;
 	mutex_lock(&device->group->device_lock);
 	list_add(&device->group_next, &device->group->device_list);
 	mutex_unlock(&device->group->device_lock);
@@ -749,6 +772,8 @@ void vfio_device_group_register(struct vfio_device *device)
 
 void vfio_device_group_unregister(struct vfio_device *device)
 {
+	if (!device->group)
+		return;
 	mutex_lock(&device->group->device_lock);
 	list_del(&device->group_next);
 	mutex_unlock(&device->group->device_lock);
@@ -786,6 +811,8 @@ void vfio_device_group_unuse_iommu(struct vfio_device *device)
 
 bool vfio_device_has_container(struct vfio_device *device)
 {
+	if (!device->group)
+		return false;
 	return device->group->container;
 }
 
-- 
2.43.0