Commit 35890f85 authored by Jason Gunthorpe's avatar Jason Gunthorpe Committed by Will Deacon
Browse files

vfio: Remove VFIO_TYPE1_NESTING_IOMMU 



This control causes the ARM SMMU drivers to choose a stage 2
implementation for the IO pagetable (vs the stage 1 usual default),
however this choice has no significant visible impact to the VFIO
user. Further qemu never implemented this and no other userspace user is
known.

The original description in commit f5c9eceb ("vfio/iommu_type1: add
new VFIO_TYPE1_NESTING_IOMMU IOMMU type") suggested this was to "provide
SMMU translation services to the guest operating system" however the rest
of the API to set the guest table pointer for the stage 1 and manage
invalidation was never completed, or at least never upstreamed, rendering
this part useless dead code.

Upstream has now settled on iommufd as the uAPI for controlling nested
translation. Choosing the stage 2 implementation should be done by through
the IOMMU_HWPT_ALLOC_NEST_PARENT flag during domain allocation.

Remove VFIO_TYPE1_NESTING_IOMMU and everything under it including the
enable_nesting iommu_domain_op.

Just in-case there is some userspace using this continue to treat
requesting it as a NOP, but do not advertise support any more.

Acked-by: default avatarAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: default avatarMostafa Saleh <smostafa@google.com>
Reviewed-by: default avatarKevin Tian <kevin.tian@intel.com>
Reviewed-by: default avatarJerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: default avatarDonald Dutile <ddutile@redhat.com>
Tested-by: default avatarNicolin Chen <nicolinc@nvidia.com>
Signed-off-by: default avatarNicolin Chen <nicolinc@nvidia.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v4-9e99b76f3518+3a8-smmuv3_nesting_jgg@nvidia.com


Signed-off-by: default avatarWill Deacon <will@kernel.org>
parent 8e929cb5

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

+0 −16
Original line number Diff line number Diff line
@@ -3378,21 +3378,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) 
	return group;

}



static int arm_smmu_enable_nesting(struct iommu_domain *domain)

{

	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	int ret = 0;



	mutex_lock(&smmu_domain->init_mutex);

	if (smmu_domain->smmu)

		ret = -EPERM;

	else

		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;

	mutex_unlock(&smmu_domain->init_mutex);



	return ret;

}



static int arm_smmu_of_xlate(struct device *dev,

			     const struct of_phandle_args *args)

{
@@ -3514,7 +3499,6 @@ static struct iommu_ops arm_smmu_ops = { 
		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,

		.iotlb_sync		= arm_smmu_iotlb_sync,

		.iova_to_phys		= arm_smmu_iova_to_phys,

		.enable_nesting		= arm_smmu_enable_nesting,

		.free			= arm_smmu_domain_free_paging,

	}

};

drivers/iommu/arm/arm-smmu/arm-smmu.c

+0 −16
Original line number Diff line number Diff line
@@ -1558,21 +1558,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) 
	return group;

}



static int arm_smmu_enable_nesting(struct iommu_domain *domain)

{

	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	int ret = 0;



	mutex_lock(&smmu_domain->init_mutex);

	if (smmu_domain->smmu)

		ret = -EPERM;

	else

		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;

	mutex_unlock(&smmu_domain->init_mutex);



	return ret;

}



static int arm_smmu_set_pgtable_quirks(struct iommu_domain *domain,

		unsigned long quirks)

{
@@ -1656,7 +1641,6 @@ static struct iommu_ops arm_smmu_ops = { 
		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,

		.iotlb_sync		= arm_smmu_iotlb_sync,

		.iova_to_phys		= arm_smmu_iova_to_phys,

		.enable_nesting		= arm_smmu_enable_nesting,

		.set_pgtable_quirks	= arm_smmu_set_pgtable_quirks,

		.free			= arm_smmu_domain_free,

	}

drivers/iommu/iommu.c

+0 −10
Original line number Diff line number Diff line
@@ -2723,16 +2723,6 @@ static int __init iommu_init(void) 
}

core_initcall(iommu_init);



int iommu_enable_nesting(struct iommu_domain *domain)

{

	if (domain->type != IOMMU_DOMAIN_UNMANAGED)

		return -EINVAL;

	if (!domain->ops->enable_nesting)

		return -EINVAL;

	return domain->ops->enable_nesting(domain);

}

EXPORT_SYMBOL_GPL(iommu_enable_nesting);



int iommu_set_pgtable_quirks(struct iommu_domain *domain,

		unsigned long quirk)

{

drivers/iommu/iommufd/vfio_compat.c

+1 −6
Original line number Diff line number Diff line
@@ -291,12 +291,7 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, 
	case VFIO_DMA_CC_IOMMU:

		return iommufd_vfio_cc_iommu(ictx);



	/*

	 * This is obsolete, and to be removed from VFIO. It was an incomplete

	 * idea that got merged.

	 * https://lore.kernel.org/kvm/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/

	 */

	case VFIO_TYPE1_NESTING_IOMMU:

	case __VFIO_RESERVED_TYPE1_NESTING_IOMMU:

		return 0;



	/*

drivers/vfio/vfio_iommu_type1.c

+1 −11
Original line number Diff line number Diff line
@@ -72,7 +72,6 @@ struct vfio_iommu { 
	uint64_t		pgsize_bitmap;

	uint64_t		num_non_pinned_groups;

	bool			v2;

	bool			nesting;

	bool			dirty_page_tracking;

	struct list_head	emulated_iommu_groups;

};
@@ -2195,12 +2194,6 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, 
		goto out_free_domain;

	}



	if (iommu->nesting) {

		ret = iommu_enable_nesting(domain->domain);

		if (ret)

			goto out_domain;

	}



	ret = iommu_attach_group(domain->domain, group->iommu_group);

	if (ret)

		goto out_domain;
@@ -2541,9 +2534,7 @@ static void *vfio_iommu_type1_open(unsigned long arg) 
	switch (arg) {

	case VFIO_TYPE1_IOMMU:

		break;

	case VFIO_TYPE1_NESTING_IOMMU:

		iommu->nesting = true;

		fallthrough;

	case __VFIO_RESERVED_TYPE1_NESTING_IOMMU:

	case VFIO_TYPE1v2_IOMMU:

		iommu->v2 = true;

		break;
@@ -2638,7 +2629,6 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu, 
	switch (arg) {

	case VFIO_TYPE1_IOMMU:

	case VFIO_TYPE1v2_IOMMU:

	case VFIO_TYPE1_NESTING_IOMMU:

	case VFIO_UNMAP_ALL:

		return 1;

	case VFIO_UPDATE_VADDR: