ENUM IOMMUFD_HWPT_ALLOC_FLAGS(9)
π
enum iommufd_hwpt_alloc_flags(9) π
okay so bestie, you found yourself in the Kernel API Manual β welcome, pull up a chair, we're talking about HWPT allocation flags today and honestly? it's giving "small enum, big responsibilities" β¨
πΈ NAME πΈ
enum iommufd_hwpt_alloc_flags β the flags you pass when you're allocating an HWPT π
β¨ SYNOPSIS β¨
enum iommufd_hwpt_alloc_flags {
IOMMU_HWPT_ALLOC_NEST_PARENT ,
IOMMU_HWPT_ALLOC_DIRTY_TRACKING ,
IOMMU_HWPT_FAULT_ID_VALID ,
IOMMU_HWPT_ALLOC_PASID
};
like, that's the whole vibe. four constants, zero drama (mostly) π¦
π Constants π
IOMMU_HWPT_ALLOC_NEST_PARENTβ set this and you get a HWPT that can serve as the parent HWPT in a nesting configuration π it's the main character of the nesting setup fr fr.IOMMU_HWPT_ALLOC_DIRTY_TRACKINGβ dirty tracking support for the device IOMMU, and heads up: this is enforced on device attachment, so it's not a "maybe later" kind of flag, it's a commitment πIOMMU_HWPT_FAULT_ID_VALIDβ tells everyone thefault_idfield of the hwpt allocation data is valid. literally that's it, that's the flag π«ΆIOMMU_HWPT_ALLOC_PASIDβ requests a domain that can be used with PASID, and that domain can be attached to any PASID on the device π but listen, there are rules:- any domain attached to the non-PASID part of the device must also be flagged, otherwise attaching a PASID will be blocked π
- if you're the user who wants to attach PASID,
ioasis not recommended for both the non-PASID part and the PASID part of the device - and if the IOMMU doesn't support PASID? it returns an error
(-EOPNOTSUPP)π no cap.
bestie pls read the PASID bullets twice, the "blocked" thing is real and it will ruin your whole afternoon π
π¦ SEE ALSO π¦
Kernel file ./include/uapi/linux/iommufd.h β go read it, it's iconic β
General ioctl format(9)struct iommu_destroy(9)struct iommu_ioas_alloc(9)struct iommu_iova_range(9)struct iommu_ioas_iova_ranges(9)struct iommu_ioas_allow_iovas(9)enum iommufd_ioas_map_flags(9)struct iommu_ioas_map(9)struct iommu_ioas_noiommu_get_pa(9)struct iommu_ioas_map_file(9)struct iommu_ioas_copy(9)struct iommu_ioas_unmap(9)enum iommufd_option(9)enum iommufd_option_ops(9)struct iommu_option(9)enum iommufd_vfio_ioas_op(9)struct iommu_vfio_ioas(9)enum iommu_hwpt_vtd_s1_flags(9)struct iommu_hwpt_vtd_s1(9)struct iommu_hwpt_arm_smmuv3(9)struct iommu_hwpt_amd_guest(9)enum iommu_hwpt_data_type(9)struct iommu_hwpt_alloc(9)enum iommu_hw_info_vtd_flags(9)struct iommu_hw_info_vtd(9)enum iommu_hw_info_arm_smmuv3_flags(9)struct iommu_hw_info_arm_smmuv3(9)struct iommu_hw_info_tegra241_cmdqv(9)struct iommu_hw_info_amd(9)enum iommu_hw_info_type(9)enum iommufd_hw_capabilities(9)enum iommufd_hw_info_flags(9)struct iommu_hw_info(9)struct iommu_hwpt_set_dirty_tracking(9)enum iommufd_hwpt_get_dirty_bitmap_flags(9)struct iommu_hwpt_get_dirty_bitmap(9)enum iommu_hwpt_invalidate_data_type(9)enum iommu_hwpt_vtd_s1_invalidate_flags(9)struct iommu_hwpt_vtd_s1_invalidate(9)struct iommu_viommu_arm_smmuv3_invalidate(9)struct iommu_hwpt_invalidate(9)enum iommu_hwpt_pgfault_flags(9)enum iommu_hwpt_pgfault_perm(9)struct iommu_hwpt_pgfault(9)enum iommufd_page_response_code(9)struct iommu_hwpt_page_response(9)struct iommu_fault_alloc(9)enum iommu_viommu_type(9)struct iommu_viommu_tegra241_cmdqv(9)struct iommu_viommu_alloc(9)struct iommu_vdevice_alloc(9)struct iommu_ioas_change_process(9)enum iommu_veventq_flag(9)struct iommufd_vevent_header(9)enum iommu_veventq_type(9)struct iommu_vevent_arm_smmuv3(9)struct iommu_vevent_tegra241_cmdqv(9)struct iommu_veventq_alloc(9)enum iommu_hw_queue_type(9)struct iommu_hw_queue_alloc(9)
like yes that's a lot of cross-references but that's the lore okay π
that's the whole page bestie!! source lives in ./include/uapi/linux and this edition is dated October 2026 β go forth and nest your HWPTs responsibly π§ββοΈππ
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms