Re: [PATCH v5 2/9] iommufd: Support a HWPT without an iommu driver for noiommu

[Yi Liu <yi.l.liu@intel.com>]

On 5/12/26 02:41, Jacob Pan wrote:
> From: Jason Gunthorpe <jgg@nvidia.com>
> 
> Create just a little part of a real iommu driver, enough to
> slot in under the dev_iommu_ops() and allow iommufd to call
> domain_alloc_paging_flags() and fail everything else.
> 
> This allows explicitly creating a HWPT under an IOAS.
> 
> A new Kconfig option IOMMUFD_NOIOMMU is introduced to differentiate
> from the VFIO group/container based noiommu mode.
> 
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
> ---
> v5:
>     - Use the new IOMMUFD_NOIOMMU Kconfig instead of VFIO_NOIOMMU
>     - Use consistent wording referring to VFIO noiommu mode (Kevin)
>     - Copyright date fix (Kevin)
> v4:
>     - Make iommufd_noiommu_ops const
> v3:
>     - Add comment to explain the design difference over the
>       legacy noiommu VFIO code.
> ---
>   drivers/iommu/iommufd/Kconfig           |  13 +++
>   drivers/iommu/iommufd/Makefile          |   1 +
>   drivers/iommu/iommufd/hw_pagetable.c    |  15 +++-
>   drivers/iommu/iommufd/hwpt_noiommu.c    | 102 ++++++++++++++++++++++++
>   drivers/iommu/iommufd/iommufd_private.h |   2 +
>   5 files changed, 131 insertions(+), 2 deletions(-)
>   create mode 100644 drivers/iommu/iommufd/hwpt_noiommu.c
> 
> diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
> index 455bac0351f2..74d6ea5b5b3b 100644
> --- a/drivers/iommu/iommufd/Kconfig
> +++ b/drivers/iommu/iommufd/Kconfig
> @@ -16,6 +16,19 @@ config IOMMUFD
>   	  If you don't know what to do here, say N.
>   
>   if IOMMUFD
> +config IOMMUFD_NOIOMMU
> +	bool
> +	depends on !GENERIC_ATOMIC64 # IOMMU_PT_AMDV1 requires cmpxchg64
> +	select GENERIC_PT
> +	select IOMMU_PT
> +	select IOMMU_PT_AMDV1
> +	help
> +	  Provides a SW-only IO page table for devices without hardware
> +	  IOMMU backing. This uses the AMDV1 page table format for
> +	  IOVA-to-PA lookups only, not for hardware DMA translation.
> +
> +	  Selected by VFIO_CDEV_NOIOMMU. Not intended to be enabled directly.
> +
>   config IOMMUFD_VFIO_CONTAINER
>   	bool "IOMMUFD provides the VFIO container /dev/vfio/vfio"
>   	depends on VFIO_GROUP && !VFIO_CONTAINER
> diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile
> index 71d692c9a8f4..67207914bb6e 100644
> --- a/drivers/iommu/iommufd/Makefile
> +++ b/drivers/iommu/iommufd/Makefile
> @@ -10,6 +10,7 @@ iommufd-y := \
>   	vfio_compat.o \
>   	viommu.o
>   
> +iommufd-$(CONFIG_IOMMUFD_NOIOMMU) += hwpt_noiommu.o
>   iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o
>   
>   obj-$(CONFIG_IOMMUFD) += iommufd.o
> diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
> index fe789c2dc0c9..0ae14cd3fc72 100644
> --- a/drivers/iommu/iommufd/hw_pagetable.c
> +++ b/drivers/iommu/iommufd/hw_pagetable.c
> @@ -8,6 +8,15 @@
>   #include "../iommu-priv.h"
>   #include "iommufd_private.h"
>   
> +static const struct iommu_ops *get_iommu_ops(struct iommufd_device *idev)
> +{
> +	if (IS_ENABLED(CONFIG_IOMMUFD_NOIOMMU) && !idev->igroup->group)
> +		return &iommufd_noiommu_ops;
> +	if (WARN_ON_ONCE(!idev->dev->iommu))
> +		return NULL;
> +	return dev_iommu_ops(idev->dev);
> +}
> +
>   static void __iommufd_hwpt_destroy(struct iommufd_hw_pagetable *hwpt)
>   {
>   	if (hwpt->domain)
> @@ -114,11 +123,13 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
>   				IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
>   				IOMMU_HWPT_FAULT_ID_VALID |
>   				IOMMU_HWPT_ALLOC_PASID;
> -	const struct iommu_ops *ops = dev_iommu_ops(idev->dev);
> +	const struct iommu_ops *ops = get_iommu_ops(idev);
>   	struct iommufd_hwpt_paging *hwpt_paging;
>   	struct iommufd_hw_pagetable *hwpt;
>   	int rc;
>   
> +	if (!ops)
> +		return ERR_PTR(-ENODEV);
>   	lockdep_assert_held(&ioas->mutex);
>   
>   	if ((flags || user_data) && !ops->domain_alloc_paging_flags)
> @@ -229,7 +240,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
>   			  struct iommufd_device *idev, u32 flags,
>   			  const struct iommu_user_data *user_data)
>   {
> -	const struct iommu_ops *ops = dev_iommu_ops(idev->dev);
> +	const struct iommu_ops *ops = get_iommu_ops(idev);
>   	struct iommufd_hwpt_nested *hwpt_nested;
>   	struct iommufd_hw_pagetable *hwpt;
>   	int rc;
> diff --git a/drivers/iommu/iommufd/hwpt_noiommu.c b/drivers/iommu/iommufd/hwpt_noiommu.c
> new file mode 100644
> index 000000000000..b1efc4bca880
> --- /dev/null
> +++ b/drivers/iommu/iommufd/hwpt_noiommu.c
> @@ -0,0 +1,102 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES
> + */
> +#include <linux/iommu.h>
> +#include <linux/generic_pt/iommu.h>
> +#include "iommufd_private.h"

you missed the comments in the below link except for the kconfig comment. :(

https://lore.kernel.org/linux-iommu/b0bf1e99-d7d0-4e62-8a97-114e8e990b58@intel.com/#t


> +
> +static const struct iommu_domain_ops noiommu_amdv1_ops;
> +
> +struct noiommu_domain {
> +	union {
> +		struct iommu_domain domain;
> +		struct pt_iommu_amdv1 amdv1;
> +	};
> +	spinlock_t lock;
> +};
> +PT_IOMMU_CHECK_DOMAIN(struct noiommu_domain, amdv1.iommu, domain);
> +
> +static void noiommu_change_top(struct pt_iommu *iommu_table,
> +			       phys_addr_t top_paddr, unsigned int top_level)
> +{
> +}
> +
> +static spinlock_t *noiommu_get_top_lock(struct pt_iommu *iommupt)
> +{
> +	struct noiommu_domain *domain =
> +		container_of(iommupt, struct noiommu_domain, amdv1.iommu);
> +
> +	return &domain->lock;
> +}
> +
> +static const struct pt_iommu_driver_ops noiommu_driver_ops = {
> +	.get_top_lock = noiommu_get_top_lock,
> +	.change_top = noiommu_change_top,
> +};
> +
> +static struct iommu_domain *
> +noiommu_alloc_paging_flags(struct device *dev, u32 flags,
> +			   const struct iommu_user_data *user_data)
> +{
> +	struct pt_iommu_amdv1_cfg cfg = {};
> +	struct noiommu_domain *dom;
> +	int rc;
> +
> +	if (flags || user_data)
> +		return ERR_PTR(-EOPNOTSUPP);
> +
> +	cfg.common.hw_max_vasz_lg2 = 64;
> +	cfg.common.hw_max_oasz_lg2 = 52;
> +	cfg.starting_level = 2;
> +	cfg.common.features =
> +		(BIT(PT_FEAT_DYNAMIC_TOP) | BIT(PT_FEAT_AMDV1_ENCRYPT_TABLES) |
> +		 BIT(PT_FEAT_AMDV1_FORCE_COHERENCE));
> +
> +	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
> +	if (!dom)
> +		return ERR_PTR(-ENOMEM);
> +
> +	spin_lock_init(&dom->lock);
> +	dom->amdv1.iommu.nid = NUMA_NO_NODE;
> +	dom->amdv1.iommu.driver_ops = &noiommu_driver_ops;
> +	dom->domain.ops = &noiommu_amdv1_ops;
> +
> +	/* Use mock page table which is based on AMDV1 */
> +	rc = pt_iommu_amdv1_init(&dom->amdv1, &cfg, GFP_KERNEL);
> +	if (rc) {
> +		kfree(dom);
> +		return ERR_PTR(rc);
> +	}
> +
> +	return &dom->domain;
> +}
> +
> +static void noiommu_domain_free(struct iommu_domain *iommu_domain)
> +{
> +	struct noiommu_domain *domain =
> +		container_of(iommu_domain, struct noiommu_domain, domain);
> +
> +	pt_iommu_deinit(&domain->amdv1.iommu);
> +	kfree(domain);
> +}
> +
> +/*
> + * AMDV1 is used as a SW-only page table for no-IOMMU mode, similar to the
> + * iommufd selftest mock page table.
> + * Unlike the VFIO group-container based no-IOMMU mode, where no container
> + * level APIs are supported, this allows IOAS and hwpt objects to exist
> + * without hardware IOMMU support. IOVAs are used only for IOVA-to-PA
> + * lookups not for hardware translation in DMA.
> + *
> + * This is only used with iommufd and cdev-based interfaces and does not
> + * apply to the VFIO group-container based noiommu mode.
> + */
> +static const struct iommu_domain_ops noiommu_amdv1_ops = {
> +	IOMMU_PT_DOMAIN_OPS(amdv1),
> +	.free = noiommu_domain_free,
> +};
> +
> +const struct iommu_ops iommufd_noiommu_ops = {
> +	.domain_alloc_paging_flags = noiommu_alloc_paging_flags,
> +};
> diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
> index 6ac1965199e9..2682b5baa6e9 100644
> --- a/drivers/iommu/iommufd/iommufd_private.h
> +++ b/drivers/iommu/iommufd/iommufd_private.h
> @@ -464,6 +464,8 @@ static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
>   	refcount_dec(&hwpt->obj.users);
>   }
>   
> +extern const struct iommu_ops iommufd_noiommu_ops;
> +
>   struct iommufd_attach;
>   
>   struct iommufd_group {