Merge patch series "Connect VFIO to IOMMUFD"

Jason Gunthorpe <jgg@nvidia.com> says:

==================
This series provides an alternative container layer for VFIO implemented
using iommufd. This is optional, if CONFIG_IOMMUFD is not set then it will
not be compiled in.

At this point iommufd can be injected by passing in a iommfd FD to
VFIO_GROUP_SET_CONTAINER which will use the VFIO compat layer in iommufd
to obtain the compat IOAS and then connect up all the VFIO drivers as
appropriate.

This is temporary stopping point, a following series will provide a way to
directly open a VFIO device FD and directly connect it to IOMMUFD using
native ioctls that can expose the IOMMUFD features like hwpt, future
vPASID and dynamic attachment.

This series, in compat mode, has passed all the qemu tests we have
available, including the test suites for the Intel GVT mdev. Aside from
the temporary limitation with P2P memory this is belived to be fully
compatible with VFIO.

This is on github: https://github.com/jgunthorpe/linux/commits/vfio_iommufd

It requires the iommufd series:

https://lore.kernel.org/r/0-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com
==================

Link: https://lore.kernel.org/r/0-v4-42cd2eb0e3eb+335a-vfio_iommufd_jgg@nvidia.comSigned-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -1484,6 +1484,9 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = {
 	.mmap		= intel_vgpu_mmap,
 	.ioctl		= intel_vgpu_ioctl,
 	.dma_unmap	= intel_vgpu_dma_unmap,
+	.bind_iommufd	= vfio_iommufd_emulated_bind,
+	.unbind_iommufd = vfio_iommufd_emulated_unbind,
+	.attach_ioas	= vfio_iommufd_emulated_attach_ioas,
 };
 
 static int intel_vgpu_probe(struct mdev_device *mdev)

drivers/iommu/iommufd/Kconfig

@@ -12,6 +12,26 @@ config IOMMUFD
 	  If you don't know what to do here, say N.
 
 if IOMMUFD
+config IOMMUFD_VFIO_CONTAINER
+	bool "IOMMUFD provides the VFIO container /dev/vfio/vfio"
+	depends on VFIO && !VFIO_CONTAINER
+	default VFIO && !VFIO_CONTAINER
+	help
+	  IOMMUFD will provide /dev/vfio/vfio instead of VFIO. This relies on
+	  IOMMUFD providing compatibility emulation to give the same ioctls.
+	  It provides an option to build a kernel with legacy VFIO components
+	  removed.
+
+	  IOMMUFD VFIO container emulation is known to lack certain features
+	  of the native VFIO container, such as no-IOMMU support, peer-to-peer
+	  DMA mapping, PPC IOMMU support, as well as other potentially
+	  undiscovered gaps.  This option is currently intended for the
+	  purpose of testing IOMMUFD with unmodified userspace supporting VFIO
+	  and making use of the Type1 VFIO IOMMU backend.  General purpose
+	  enabling of this option is currently discouraged.
+
+	  Unless testing IOMMUFD, say N here.
+
 config IOMMUFD_TEST
 	bool "IOMMU Userspace API Test support"
 	depends on DEBUG_KERNEL

drivers/iommu/iommufd/main.c

@@ -18,6 +18,7 @@
 #include <uapi/linux/iommufd.h>
 #include <linux/iommufd.h>
 
+#include "io_pagetable.h"
 #include "iommufd_private.h"
 #include "iommufd_test.h"
 
@@ -25,6 +26,7 @@ struct iommufd_object_ops {
 	void (*destroy)(struct iommufd_object *obj);
 };
 static const struct iommufd_object_ops iommufd_object_ops[];
+static struct miscdevice vfio_misc_dev;
 
 struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
@@ -170,6 +172,16 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	if (!ictx)
 		return -ENOMEM;
 
+	/*
+	 * For compatibility with VFIO when /dev/vfio/vfio is opened we default
+	 * to the same rlimit accounting as vfio uses.
+	 */
+	if (IS_ENABLED(CONFIG_IOMMUFD_VFIO_CONTAINER) &&
+	    filp->private_data == &vfio_misc_dev) {
+		ictx->account_mode = IOPT_PAGES_ACCOUNT_MM;
+		pr_info_once("IOMMUFD is providing /dev/vfio/vfio, not VFIO.\n");
+	}
+
 	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
 	ictx->file = filp;
 	filp->private_data = ictx;
@@ -400,6 +412,15 @@ static struct miscdevice iommu_misc_dev = {
 	.mode = 0660,
 };
 
+
+static struct miscdevice vfio_misc_dev = {
+	.minor = VFIO_MINOR,
+	.name = "vfio",
+	.fops = &iommufd_fops,
+	.nodename = "vfio/vfio",
+	.mode = 0666,
+};
+
 static int __init iommufd_init(void)
 {
 	int ret;
@@ -407,18 +428,33 @@ static int __init iommufd_init(void)
 	ret = misc_register(&iommu_misc_dev);
 	if (ret)
 		return ret;
+
+	if (IS_ENABLED(CONFIG_IOMMUFD_VFIO_CONTAINER)) {
+		ret = misc_register(&vfio_misc_dev);
+		if (ret)
+			goto err_misc;
+	}
 	iommufd_test_init();
 	return 0;
+err_misc:
+	misc_deregister(&iommu_misc_dev);
+	return ret;
 }
 
 static void __exit iommufd_exit(void)
 {
 	iommufd_test_exit();
+	if (IS_ENABLED(CONFIG_IOMMUFD_VFIO_CONTAINER))
+		misc_deregister(&vfio_misc_dev);
 	misc_deregister(&iommu_misc_dev);
 }
 
 module_init(iommufd_init);
 module_exit(iommufd_exit);
 
+#if IS_ENABLED(CONFIG_IOMMUFD_VFIO_CONTAINER)
+MODULE_ALIAS_MISCDEV(VFIO_MINOR);
+MODULE_ALIAS("devname:vfio/vfio");
+#endif
 MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices");
 MODULE_LICENSE("GPL");

drivers/s390/cio/vfio_ccw_ops.c

@@ -588,6 +588,9 @@ static const struct vfio_device_ops vfio_ccw_dev_ops = {
 	.ioctl = vfio_ccw_mdev_ioctl,
 	.request = vfio_ccw_mdev_request,
 	.dma_unmap = vfio_ccw_dma_unmap,
+	.bind_iommufd = vfio_iommufd_emulated_bind,
+	.unbind_iommufd = vfio_iommufd_emulated_unbind,
+	.attach_ioas = vfio_iommufd_emulated_attach_ioas,
 };
 
 struct mdev_driver vfio_ccw_mdev_driver = {

drivers/s390/crypto/vfio_ap_ops.c

@@ -1805,6 +1805,9 @@ static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
 	.close_device = vfio_ap_mdev_close_device,
 	.ioctl = vfio_ap_mdev_ioctl,
 	.dma_unmap = vfio_ap_mdev_dma_unmap,
+	.bind_iommufd = vfio_iommufd_emulated_bind,
+	.unbind_iommufd = vfio_iommufd_emulated_unbind,
+	.attach_ioas = vfio_iommufd_emulated_attach_ioas,
 };
 
 static struct mdev_driver vfio_ap_matrix_driver = {

drivers/vfio/Kconfig

@@ -2,8 +2,9 @@
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	select IOMMU_API
-	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+	depends on IOMMUFD || !IOMMUFD
 	select INTERVAL_TREE
+	select VFIO_CONTAINER if IOMMUFD=n
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/driver-api/vfio.rst for more details.
@@ -11,6 +12,18 @@ menuconfig VFIO
 	  If you don't know what to do here, say N.
 
 if VFIO
+config VFIO_CONTAINER
+	bool "Support for the VFIO container /dev/vfio/vfio"
+	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+	default y
+	help
+	  The VFIO container is the classic interface to VFIO for establishing
+	  IOMMU mappings. If N is selected here then IOMMUFD must be used to
+	  manage the mappings.
+
+	  Unless testing IOMMUFD say Y here.
+
+if VFIO_CONTAINER
 config VFIO_IOMMU_TYPE1
 	tristate
 	default n
@@ -20,16 +33,6 @@ config VFIO_IOMMU_SPAPR_TCE
 	depends on SPAPR_TCE_IOMMU
 	default VFIO
 
-config VFIO_SPAPR_EEH
-	tristate
-	depends on EEH && VFIO_IOMMU_SPAPR_TCE
-	default VFIO
-
-config VFIO_VIRQFD
-	tristate
-	select EVENTFD
-	default n
-
 config VFIO_NOIOMMU
 	bool "VFIO No-IOMMU support"
 	help
@@ -43,6 +46,17 @@ config VFIO_NOIOMMU
 	  this mode since there is no IOMMU to provide DMA translation.
 
 	  If you don't know what to do here, say N.
+endif
+
+config VFIO_SPAPR_EEH
+	tristate
+	depends on EEH && VFIO_IOMMU_SPAPR_TCE
+	default VFIO
+
+config VFIO_VIRQFD
+	tristate
+	select EVENTFD
+	default n
 
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"

drivers/vfio/Makefile

@@ -4,8 +4,9 @@ vfio_virqfd-y := virqfd.o
 obj-$(CONFIG_VFIO) += vfio.o
 
 vfio-y += vfio_main.o \
-	  iova_bitmap.o \
-	  container.o
+	  iova_bitmap.o
+vfio-$(CONFIG_IOMMUFD) += iommufd.o
+vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 
 obj-$(CONFIG_VFIO_VIRQFD) += vfio_virqfd.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o

drivers/vfio/container.c

@@ -188,8 +188,9 @@ void vfio_device_container_unregister(struct vfio_device *device)
 			device->group->container->iommu_data, device);
 }
 
-long vfio_container_ioctl_check_extension(struct vfio_container *container,
-					  unsigned long arg)
+static long
+vfio_container_ioctl_check_extension(struct vfio_container *container,
+				     unsigned long arg)
 {
 	struct vfio_iommu_driver *driver;
 	long ret = 0;
@@ -511,14 +512,15 @@ void vfio_group_detach_container(struct vfio_group *group)
 	vfio_container_put(container);
 }
 
-int vfio_device_assign_container(struct vfio_device *device)
+int vfio_group_use_container(struct vfio_group *group)
 {
-	struct vfio_group *group = device->group;
-
 	lockdep_assert_held(&group->group_lock);
 
-	if (!group->container || !group->container->iommu_driver ||
-	    WARN_ON(!group->container_users))
+	/*
+	 * The container fd has been assigned with VFIO_GROUP_SET_CONTAINER but
+	 * VFIO_SET_IOMMU hasn't been done yet.
+	 */
+	if (!group->container->iommu_driver)
 		return -EINVAL;
 
 	if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO))
@@ -529,122 +531,50 @@ int vfio_device_assign_container(struct vfio_device *device)
 	return 0;
 }
 
-void vfio_device_unassign_container(struct vfio_device *device)
+void vfio_group_unuse_container(struct vfio_group *group)
 {
-	mutex_lock(&device->group->group_lock);
-	WARN_ON(device->group->container_users <= 1);
-	device->group->container_users--;
-	fput(device->group->opened_file);
-	mutex_unlock(&device->group->group_lock);
+	lockdep_assert_held(&group->group_lock);
+
+	WARN_ON(group->container_users <= 1);
+	group->container_users--;
+	fput(group->opened_file);
 }
 
-/*
- * Pin contiguous user pages and return their associated host pages for local
- * domain only.
- * @device [in]  : device
- * @iova [in]    : starting IOVA of user pages to be pinned.
- * @npage [in]   : count of pages to be pinned.  This count should not
- *		   be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
- * @prot [in]    : protection flags
- * @pages[out]   : array of host pages
- * Return error or number of pages pinned.
- *
- * A driver may only call this function if the vfio_device was created
- * by vfio_register_emulated_iommu_dev().
- */
-int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
-		   int npage, int prot, struct page **pages)
+int vfio_container_pin_pages(struct vfio_container *container,
+			     struct iommu_group *iommu_group, dma_addr_t iova,
+			     int npage, int prot, struct page **pages)
 {
-	struct vfio_container *container;
-	struct vfio_group *group = device->group;
-	struct vfio_iommu_driver *driver;
-	int ret;
-
-	if (!pages || !npage || !vfio_assert_device_open(device))
-		return -EINVAL;
+	struct vfio_iommu_driver *driver = container->iommu_driver;
 
 	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
 		return -E2BIG;
 
-	/* group->container cannot change while a vfio device is open */
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->pin_pages))
-		ret = driver->ops->pin_pages(container->iommu_data,
-					     group->iommu_group, iova,
-					     npage, prot, pages);
-	else
-		ret = -ENOTTY;
-
-	return ret;
+	if (unlikely(!driver || !driver->ops->pin_pages))
+		return -ENOTTY;
+	return driver->ops->pin_pages(container->iommu_data, iommu_group, iova,
+				      npage, prot, pages);
 }
-EXPORT_SYMBOL(vfio_pin_pages);
 
-/*
- * Unpin contiguous host pages for local domain only.
- * @device [in]  : device
- * @iova [in]    : starting address of user pages to be unpinned.
- * @npage [in]   : count of pages to be unpinned.  This count should not
- *                 be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
- */
-void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
+void vfio_container_unpin_pages(struct vfio_container *container,
+				dma_addr_t iova, int npage)
 {
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-
 	if (WARN_ON(npage <= 0 || npage > VFIO_PIN_PAGES_MAX_ENTRIES))
 		return;
 
-	if (WARN_ON(!vfio_assert_device_open(device)))
-		return;
-
-	/* group->container cannot change while a vfio device is open */
-	container = device->group->container;
-	driver = container->iommu_driver;
-
-	driver->ops->unpin_pages(container->iommu_data, iova, npage);
+	container->iommu_driver->ops->unpin_pages(container->iommu_data, iova,
+						  npage);
 }
-EXPORT_SYMBOL(vfio_unpin_pages);
 
-/*
- * This interface allows the CPUs to perform some sort of virtual DMA on
- * behalf of the device.
- *
- * CPUs read/write from/into a range of IOVAs pointing to user space memory
- * into/from a kernel buffer.
- *
- * As the read/write of user space memory is conducted via the CPUs and is
- * not a real device DMA, it is not necessary to pin the user space memory.
- *
- * @device [in]		: VFIO device
- * @iova [in]		: base IOVA of a user space buffer
- * @data [in]		: pointer to kernel buffer
- * @len [in]		: kernel buffer length
- * @write		: indicate read or write
- * Return error code on failure or 0 on success.
- */
-int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data,
-		size_t len, bool write)
+int vfio_container_dma_rw(struct vfio_container *container, dma_addr_t iova,
+			  void *data, size_t len, bool write)
 {
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-	int ret = 0;
-
-	if (!data || len <= 0 || !vfio_assert_device_open(device))
-		return -EINVAL;
-
-	/* group->container cannot change while a vfio device is open */
-	container = device->group->container;
-	driver = container->iommu_driver;
+	struct vfio_iommu_driver *driver = container->iommu_driver;
 
-	if (likely(driver && driver->ops->dma_rw))
-		ret = driver->ops->dma_rw(container->iommu_data,
-					  iova, data, len, write);
-	else
-		ret = -ENOTTY;
-	return ret;
+	if (unlikely(!driver || !driver->ops->dma_rw))
+		return -ENOTTY;
+	return driver->ops->dma_rw(container->iommu_data, iova, data, len,
+				   write);
 }
-EXPORT_SYMBOL(vfio_dma_rw);
 
 int __init vfio_container_init(void)
 {
@@ -678,3 +608,6 @@ void vfio_container_cleanup(void)
 	misc_deregister(&vfio_dev);
 	mutex_destroy(&vfio.iommu_drivers_lock);
 }
+
+MODULE_ALIAS_MISCDEV(VFIO_MINOR);
+MODULE_ALIAS("devname:vfio/vfio");

drivers/vfio/fsl-mc/vfio_fsl_mc.c

@@ -592,6 +592,9 @@ static const struct vfio_device_ops vfio_fsl_mc_ops = {
 	.read		= vfio_fsl_mc_read,
 	.write		= vfio_fsl_mc_write,
 	.mmap		= vfio_fsl_mc_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
 };
 
 static struct fsl_mc_driver vfio_fsl_mc_driver = {

drivers/vfio/iommufd.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES
+ */
+#include <linux/vfio.h>
+#include <linux/iommufd.h>
+
+#include "vfio.h"
+
+MODULE_IMPORT_NS(IOMMUFD);
+MODULE_IMPORT_NS(IOMMUFD_VFIO);
+
+int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx)
+{
+	u32 ioas_id;
+	u32 device_id;
+	int ret;
+
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	/*
+	 * If the driver doesn't provide this op then it means the device does
+	 * not do DMA at all. So nothing to do.
+	 */
+	if (!vdev->ops->bind_iommufd)
+		return 0;
+
+	ret = vdev->ops->bind_iommufd(vdev, ictx, &device_id);
+	if (ret)
+		return ret;
+
+	ret = iommufd_vfio_compat_ioas_id(ictx, &ioas_id);
+	if (ret)
+		goto err_unbind;
+	ret = vdev->ops->attach_ioas(vdev, &ioas_id);
+	if (ret)
+		goto err_unbind;
+
+	/*
+	 * The legacy path has no way to return the device id or the selected
+	 * pt_id
+	 */
+	return 0;
+
+err_unbind:
+	if (vdev->ops->unbind_iommufd)
+		vdev->ops->unbind_iommufd(vdev);
+	return ret;
+}
+
+void vfio_iommufd_unbind(struct vfio_device *vdev)
+{
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	if (vdev->ops->unbind_iommufd)
+		vdev->ops->unbind_iommufd(vdev);
+}
+
+/*
+ * The physical standard ops mean that the iommufd_device is bound to the
+ * physical device vdev->dev that was provided to vfio_init_group_dev(). Drivers
+ * using this ops set should call vfio_register_group_dev()
+ */
+int vfio_iommufd_physical_bind(struct vfio_device *vdev,
+			       struct iommufd_ctx *ictx, u32 *out_device_id)
+{
+	struct iommufd_device *idev;
+
+	idev = iommufd_device_bind(ictx, vdev->dev, out_device_id);
+	if (IS_ERR(idev))
+		return PTR_ERR(idev);
+	vdev->iommufd_device = idev;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_bind);
+
+void vfio_iommufd_physical_unbind(struct vfio_device *vdev)
+{
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	if (vdev->iommufd_attached) {
+		iommufd_device_detach(vdev->iommufd_device);
+		vdev->iommufd_attached = false;
+	}
+	iommufd_device_unbind(vdev->iommufd_device);
+	vdev->iommufd_device = NULL;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_unbind);
+
+int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id)
+{
+	int rc;
+
+	rc = iommufd_device_attach(vdev->iommufd_device, pt_id);
+	if (rc)
+		return rc;
+	vdev->iommufd_attached = true;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_attach_ioas);
+
+/*
+ * The emulated standard ops mean that vfio_device is going to use the
+ * "mdev path" and will call vfio_pin_pages()/vfio_dma_rw(). Drivers using this
+ * ops set should call vfio_register_emulated_iommu_dev().
+ */
+
+static void vfio_emulated_unmap(void *data, unsigned long iova,
+				unsigned long length)
+{
+	struct vfio_device *vdev = data;
+
+	vdev->ops->dma_unmap(vdev, iova, length);
+}
+
+static const struct iommufd_access_ops vfio_user_ops = {
+	.needs_pin_pages = 1,
+	.unmap = vfio_emulated_unmap,
+};
+
+int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
+			       struct iommufd_ctx *ictx, u32 *out_device_id)
+{
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	vdev->iommufd_ictx = ictx;
+	iommufd_ctx_get(ictx);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_bind);
+
+void vfio_iommufd_emulated_unbind(struct vfio_device *vdev)
+{
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	if (vdev->iommufd_access) {
+		iommufd_access_destroy(vdev->iommufd_access);
+		vdev->iommufd_access = NULL;
+	}
+	iommufd_ctx_put(vdev->iommufd_ictx);
+	vdev->iommufd_ictx = NULL;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_unbind);
+
+int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id)
+{
+	struct iommufd_access *user;
+
+	lockdep_assert_held(&vdev->dev_set->lock);
+
+	user = iommufd_access_create(vdev->iommufd_ictx, *pt_id, &vfio_user_ops,
+				     vdev);
+	if (IS_ERR(user))
+		return PTR_ERR(user);
+	vdev->iommufd_access = user;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_attach_ioas);

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c

@@ -1246,6 +1246,9 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = {
 	.mmap = hisi_acc_vfio_pci_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
 };
 
 static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
@@ -1261,6 +1264,9 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
 };
 
 static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)

drivers/vfio/pci/mlx5/main.c

@@ -623,6 +623,9 @@ static const struct vfio_device_ops mlx5vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
 };
 
 static int mlx5vf_pci_probe(struct pci_dev *pdev,

drivers/vfio/pci/vfio_pci.c

@@ -138,6 +138,9 @@ static const struct vfio_device_ops vfio_pci_ops = {
 	.mmap		= vfio_pci_core_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
 };
 
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)

drivers/vfio/platform/vfio_amba.c

@@ -117,6 +117,9 @@ static const struct vfio_device_ops vfio_amba_ops = {
 	.read		= vfio_platform_read,
 	.write		= vfio_platform_write,
 	.mmap		= vfio_platform_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
 };
 
 static const struct amba_id pl330_ids[] = {

drivers/vfio/platform/vfio_platform.c

@@ -106,6 +106,9 @@ static const struct vfio_device_ops vfio_platform_ops = {
 	.read		= vfio_platform_read,
 	.write		= vfio_platform_write,
 	.mmap		= vfio_platform_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
 };
 
 static struct platform_driver vfio_platform_driver = {

drivers/vfio/vfio.h

@@ -10,6 +10,7 @@
 #include <linux/cdev.h>
 #include <linux/module.h>
 
+struct iommufd_ctx;
 struct iommu_group;
 struct vfio_device;
 struct vfio_container;
@@ -54,14 +55,18 @@ struct vfio_group {
 	struct list_head		device_list;
 	struct mutex			device_lock;
 	struct list_head		vfio_next;
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
 	struct list_head		container_next;
+#endif
 	enum vfio_group_type		type;
 	struct mutex			group_lock;
 	struct kvm			*kvm;
 	struct file			*opened_file;
 	struct blocking_notifier_head	notifier;
+	struct iommufd_ctx		*iommufd;
 };
 
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
 /* events for the backend driver notify callback */
 enum vfio_iommu_notify_type {
 	VFIO_IOMMU_CONTAINER_CLOSE = 0,
@@ -109,20 +114,101 @@ struct vfio_iommu_driver {
 int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
 void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops);
 
-bool vfio_assert_device_open(struct vfio_device *device);
-
 struct vfio_container *vfio_container_from_file(struct file *filep);
-int vfio_device_assign_container(struct vfio_device *device);
-void vfio_device_unassign_container(struct vfio_device *device);
+int vfio_group_use_container(struct vfio_group *group);
+void vfio_group_unuse_container(struct vfio_group *group);
 int vfio_container_attach_group(struct vfio_container *container,
 				struct vfio_group *group);
 void vfio_group_detach_container(struct vfio_group *group);
 void vfio_device_container_register(struct vfio_device *device);
 void vfio_device_container_unregister(struct vfio_device *device);
-long vfio_container_ioctl_check_extension(struct vfio_container *container,
-					  unsigned long arg);
+int vfio_container_pin_pages(struct vfio_container *container,
+			     struct iommu_group *iommu_group, dma_addr_t iova,
+			     int npage, int prot, struct page **pages);
+void vfio_container_unpin_pages(struct vfio_container *container,
+				dma_addr_t iova, int npage);
+int vfio_container_dma_rw(struct vfio_container *container, dma_addr_t iova,
+			  void *data, size_t len, bool write);
+
 int __init vfio_container_init(void);
 void vfio_container_cleanup(void);
+#else
+static inline struct vfio_container *
+vfio_container_from_file(struct file *filep)
+{
+	return NULL;
+}
+
+static inline int vfio_group_use_container(struct vfio_group *group)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_unuse_container(struct vfio_group *group)
+{
+}
+
+static inline int vfio_container_attach_group(struct vfio_container *container,
+					      struct vfio_group *group)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_detach_container(struct vfio_group *group)
+{
+}
+
+static inline void vfio_device_container_register(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_container_unregister(struct vfio_device *device)
+{
+}
+
+static inline int vfio_container_pin_pages(struct vfio_container *container,
+					   struct iommu_group *iommu_group,
+					   dma_addr_t iova, int npage, int prot,
+					   struct page **pages)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void vfio_container_unpin_pages(struct vfio_container *container,
+					      dma_addr_t iova, int npage)
+{
+}
+
+static inline int vfio_container_dma_rw(struct vfio_container *container,
+					dma_addr_t iova, void *data, size_t len,
+					bool write)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int vfio_container_init(void)
+{
+	return 0;
+}
+static inline void vfio_container_cleanup(void)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IOMMUFD)
+int vfio_iommufd_bind(struct vfio_device *device, struct iommufd_ctx *ictx);
+void vfio_iommufd_unbind(struct vfio_device *device);
+#else
+static inline int vfio_iommufd_bind(struct vfio_device *device,
+				    struct iommufd_ctx *ictx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void vfio_iommufd_unbind(struct vfio_device *device)
+{
+}
+#endif
 
 #ifdef CONFIG_VFIO_NOIOMMU
 extern bool vfio_noiommu __read_mostly;

include/linux/vfio.h

@@ -17,6 +17,9 @@
 #include <linux/iova_bitmap.h>
 
 struct kvm;
+struct iommufd_ctx;
+struct iommufd_device;
+struct iommufd_access;
 
 /*
  * VFIO devices can be placed in a set, this allows all devices to share this
@@ -54,6 +57,12 @@ struct vfio_device {
 	struct completion comp;
 	struct list_head group_next;
 	struct list_head iommu_entry;
+	struct iommufd_access *iommufd_access;
+#if IS_ENABLED(CONFIG_IOMMUFD)
+	struct iommufd_device *iommufd_device;
+	struct iommufd_ctx *iommufd_ictx;
+	bool iommufd_attached;
+#endif
 };
 
 /**
@@ -80,6 +89,10 @@ struct vfio_device_ops {
 	char	*name;
 	int	(*init)(struct vfio_device *vdev);
 	void	(*release)(struct vfio_device *vdev);
+	int	(*bind_iommufd)(struct vfio_device *vdev,
+				struct iommufd_ctx *ictx, u32 *out_device_id);
+	void	(*unbind_iommufd)(struct vfio_device *vdev);
+	int	(*attach_ioas)(struct vfio_device *vdev, u32 *pt_id);
 	int	(*open_device)(struct vfio_device *vdev);
 	void	(*close_device)(struct vfio_device *vdev);
 	ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -96,6 +109,32 @@ struct vfio_device_ops {
 				  void __user *arg, size_t argsz);
 };
 
+#if IS_ENABLED(CONFIG_IOMMUFD)
+int vfio_iommufd_physical_bind(struct vfio_device *vdev,
+			       struct iommufd_ctx *ictx, u32 *out_device_id);
+void vfio_iommufd_physical_unbind(struct vfio_device *vdev);
+int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
+int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
+			       struct iommufd_ctx *ictx, u32 *out_device_id);
+void vfio_iommufd_emulated_unbind(struct vfio_device *vdev);
+int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
+#else
+#define vfio_iommufd_physical_bind                                      \
+	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
+		  u32 *out_device_id)) NULL)
+#define vfio_iommufd_physical_unbind \
+	((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_physical_attach_ioas \
+	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#define vfio_iommufd_emulated_bind                                      \
+	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
+		  u32 *out_device_id)) NULL)
+#define vfio_iommufd_emulated_unbind \
+	((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_emulated_attach_ioas \
+	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#endif
+
 /**
  * @migration_set_state: Optional callback to change the migration state for
  *         devices that support migration. It's mandatory for