@@ -14,8 +14,8 @@ config IOMMUFD
if IOMMUFD
config IOMMUFD_VFIO_CONTAINER
bool "IOMMUFD provides the VFIO container /dev/vfio/vfio"
- depends on VFIO && !VFIO_CONTAINER
- default VFIO && !VFIO_CONTAINER
+ depends on VFIO_GROUP && !VFIO_CONTAINER
+ default VFIO_GROUP && !VFIO_CONTAINER
help
IOMMUFD will provide /dev/vfio/vfio instead of VFIO. This relies on
IOMMUFD providing compatibility emulation to give the same ioctls.
@@ -4,6 +4,8 @@ menuconfig VFIO
select IOMMU_API
depends on IOMMUFD || !IOMMUFD
select INTERVAL_TREE
+ select VFIO_GROUP if SPAPR_TCE_IOMMU || IOMMUFD=n
+ select VFIO_DEVICE_CDEV if !VFIO_GROUP
select VFIO_CONTAINER if IOMMUFD=n
help
VFIO provides a framework for secure userspace device drivers.
@@ -15,6 +17,7 @@ if VFIO
config VFIO_DEVICE_CDEV
bool "Support for the VFIO cdev /dev/vfio/devices/vfioX"
depends on IOMMUFD
+ default !VFIO_GROUP
help
The VFIO device cdev is another way for userspace to get device
access. Userspace gets device fd by opening device cdev under
@@ -23,9 +26,20 @@ config VFIO_DEVICE_CDEV
If you don't know what to do here, say N.
+config VFIO_GROUP
+ bool "Support for the VFIO group /dev/vfio/$group_id"
+ default y
+ help
+ VFIO group support provides the traditional model for accessing
+ devices through VFIO and is used by the majority of userspace
+ applications and drivers making use of VFIO.
+
+ If you don't know what to do here, say Y.
+
config VFIO_CONTAINER
bool "Support for the VFIO container /dev/vfio/vfio"
select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+ depends on VFIO_GROUP
default y
help
The VFIO container is the classic interface to VFIO for establishing
@@ -2,9 +2,9 @@
obj-$(CONFIG_VFIO) += vfio.o
vfio-y += vfio_main.o \
- group.o \
iova_bitmap.o
vfio-$(CONFIG_VFIO_DEVICE_CDEV) += device_cdev.o
+vfio-$(CONFIG_VFIO_GROUP) += group.o
vfio-$(CONFIG_IOMMUFD) += iommufd.o
vfio-$(CONFIG_VFIO_CONTAINER) += container.o
vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
@@ -798,6 +798,9 @@ vfio_devset_iommufd_has_group(struct vfio_device_set *dev_set,
lockdep_assert_held(&dev_set->lock);
+ if (!iommu_group)
+ return false;
+
list_for_each_entry(cur, &dev_set->device_list, dev_set_list) {
grp = iommu_group_get(cur->dev);
if (!grp)
@@ -840,8 +843,19 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
return -EAGAIN; /* Something changed, try again */
iommu_group = iommu_group_get(&pdev->dev);
- if (!iommu_group)
- return -EPERM; /* Cannot reset non-isolated devices */
+ /*
+ * With CONFIG_VFIO_GROUP enabled, device should always have
+ * iommu_group.
+ */
+ if (IS_ENABLED(CONFIG_VFIO_GROUP) && !iommu_group)
+ return -EPERM;
+
+ /*
+ * With CONFIG_VFIO_GROUP disabled, only cdev interface is
+ * available.
+ */
+ if (WARN_ON(unlikely(!IS_ENABLED(CONFIG_VFIO_GROUP) && !fill->devid)))
+ return -EINVAL;
if (fill->devid) {
struct vfio_device *vdev;
@@ -875,7 +889,8 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
fill->devices[fill->cur].bus = pdev->bus->number;
fill->devices[fill->cur].devfn = pdev->devfn;
fill->cur++;
- iommu_group_put(iommu_group);
+ if (iommu_group)
+ iommu_group_put(iommu_group);
return 0;
}
@@ -36,6 +36,12 @@ vfio_allocate_device_file(struct vfio_device *device);
extern const struct file_operations vfio_device_fops;
+#ifdef CONFIG_VFIO_NOIOMMU
+extern bool vfio_noiommu __read_mostly;
+#else
+enum { vfio_noiommu = false };
+#endif
+
enum vfio_group_type {
/*
* Physical device with IOMMU backing.
@@ -60,6 +66,7 @@ enum vfio_group_type {
VFIO_NO_IOMMU,
};
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
struct vfio_group {
struct device dev;
struct cdev cdev;
@@ -112,6 +119,95 @@ static inline int vfio_device_set_noiommu(struct vfio_device *device)
device->group->type == VFIO_NO_IOMMU;
return 0;
}
+#else
+struct vfio_group;
+
+static inline int vfio_device_block_group(struct vfio_device *device)
+{
+ return 0;
+}
+
+static inline void vfio_device_unblock_group(struct vfio_device *device)
+{
+}
+
+static inline int vfio_device_set_group(struct vfio_device *device,
+ enum vfio_group_type type)
+{
+ return 0;
+}
+
+static inline void vfio_device_remove_group(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_group_register(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_group_unregister(struct vfio_device *device)
+{
+}
+
+static inline int vfio_device_group_use_iommu(struct vfio_device *device)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_device_group_unuse_iommu(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_group_close(struct vfio_device_file *df)
+{
+}
+
+static inline struct vfio_group *vfio_group_from_file(struct file *file)
+{
+ return NULL;
+}
+
+static inline bool vfio_group_enforced_coherent(struct vfio_group *group)
+{
+ return true;
+}
+
+static inline void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
+{
+}
+
+static inline bool vfio_device_has_container(struct vfio_device *device)
+{
+ return false;
+}
+
+static inline int __init vfio_group_init(void)
+{
+ return 0;
+}
+
+static inline void vfio_group_cleanup(void)
+{
+}
+
+static inline int vfio_device_set_noiommu(struct vfio_device *device)
+{
+ struct iommu_group *iommu_group;
+
+ device->noiommu = false;
+
+ iommu_group = iommu_group_get(device->dev);
+ if (!iommu_group) {
+ if (!IS_ENABLED(CONFIG_VFIO_NOIOMMU) || !vfio_noiommu)
+ return -EINVAL;
+ device->noiommu = vfio_noiommu;
+ } else {
+ iommu_group_put(iommu_group);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_VFIO_GROUP */
#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
/**
@@ -357,12 +453,6 @@ static inline void vfio_virqfd_exit(void)
}
#endif
-#ifdef CONFIG_VFIO_NOIOMMU
-extern bool vfio_noiommu __read_mostly;
-#else
-enum { vfio_noiommu = false };
-#endif
-
#ifdef CONFIG_HAVE_KVM
void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm);
void vfio_device_put_kvm(struct vfio_device *device);
@@ -43,7 +43,11 @@ struct vfio_device {
*/
const struct vfio_migration_ops *mig_ops;
const struct vfio_log_ops *log_ops;
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
struct vfio_group *group;
+ struct list_head group_next;
+ struct list_head iommu_entry;
+#endif
struct vfio_device_set *dev_set;
struct list_head dev_set_list;
unsigned int migration_flags;
@@ -59,8 +63,6 @@ struct vfio_device {
refcount_t refcount; /* user count on registered device*/
unsigned int open_count;
struct completion comp;
- struct list_head group_next;
- struct list_head iommu_entry;
struct iommufd_access *iommufd_access;
void (*put_kvm)(struct kvm *kvm);
#if IS_ENABLED(CONFIG_IOMMUFD)
@@ -290,12 +292,29 @@ int vfio_mig_get_next_state(struct vfio_device *device,
/*
* External user API
*/
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
struct iommu_group *vfio_file_iommu_group(struct file *file);
bool vfio_file_is_group(struct file *file);
+bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
+#else
+static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
+{
+ return NULL;
+}
+
+static inline bool vfio_file_is_group(struct file *file)
+{
+ return false;
+}
+
+static inline bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
+{
+ return false;
+}
+#endif
bool vfio_file_is_valid(struct file *file);
bool vfio_file_enforced_coherent(struct file *file);
void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
-bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
#define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long))
group code is not needed for vfio device cdev, so with vfio device cdev introduced, the group infrastructures can be compiled out if only cdev is needed. Signed-off-by: Yi Liu <yi.l.liu@intel.com> --- drivers/iommu/iommufd/Kconfig | 4 +- drivers/vfio/Kconfig | 14 +++++ drivers/vfio/Makefile | 2 +- drivers/vfio/pci/vfio_pci_core.c | 21 ++++++- drivers/vfio/vfio.h | 102 +++++++++++++++++++++++++++++-- include/linux/vfio.h | 25 +++++++- 6 files changed, 153 insertions(+), 15 deletions(-)