diff options
author | Linus Torvalds | 2023-11-01 16:44:56 -1000 |
---|---|---|
committer | Linus Torvalds | 2023-11-01 16:44:56 -1000 |
commit | 463f46e114f74465cf8d01b124e7b74ad1ce2afd (patch) | |
tree | 67ba1f82d7a3baba926eab2a896b0f4c4f3aced2 /include/uapi | |
parent | ff269e2cd5adce4ae14f883fc9c8803bc43ee1e9 (diff) | |
parent | b2b67c997bf74453f3469d8b54e4859f190943bd (diff) |
Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd
Pull iommufd updates from Jason Gunthorpe:
"This brings three new iommufd capabilities:
- Dirty tracking for DMA.
AMD/ARM/Intel CPUs can now record if a DMA writes to a page in the
IOPTEs within the IO page table. This can be used to generate a
record of what memory is being dirtied by DMA activities during a
VM migration process. A VMM like qemu will combine the IOMMU dirty
bits with the CPU's dirty log to determine what memory to transfer.
VFIO already has a DMA dirty tracking framework that requires PCI
devices to implement tracking HW internally. The iommufd version
provides an alternative that the VMM can select, if available. The
two are designed to have very similar APIs.
- Userspace controlled attributes for hardware page tables
(HWPT/iommu_domain). There are currently a few generic attributes
for HWPTs (support dirty tracking, and parent of a nest). This is
an entry point for the userspace iommu driver to control the HW in
detail.
- Nested translation support for HWPTs. This is a 2D translation
scheme similar to the CPU where a DMA goes through a first stage to
determine an intermediate address which is then translated trough a
second stage to a physical address.
Like for CPU translation the first stage table would exist in VM
controlled memory and the second stage is in the kernel and matches
the VM's guest to physical map.
As every IOMMU has a unique set of parameter to describe the S1 IO
page table and its associated parameters the userspace IOMMU driver
has to marshal the information into the correct format.
This is 1/3 of the feature, it allows creating the nested
translation and binding it to VFIO devices, however the API to
support IOTLB and ATC invalidation of the stage 1 io page table,
and forwarding of IO faults are still in progress.
The series includes AMD and Intel support for dirty tracking. Intel
support for nested translation.
Along the way are a number of internal items:
- New iommu core items: ops->domain_alloc_user(),
ops->set_dirty_tracking, ops->read_and_clear_dirty(),
IOMMU_DOMAIN_NESTED, and iommu_copy_struct_from_user
- UAF fix in iopt_area_split()
- Spelling fixes and some test suite improvement"
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (52 commits)
iommufd: Organize the mock domain alloc functions closer to Joerg's tree
iommufd/selftest: Fix page-size check in iommufd_test_dirty()
iommufd: Add iopt_area_alloc()
iommufd: Fix missing update of domains_itree after splitting iopt_area
iommu/vt-d: Disallow read-only mappings to nest parent domain
iommu/vt-d: Add nested domain allocation
iommu/vt-d: Set the nested domain to a device
iommu/vt-d: Make domain attach helpers to be extern
iommu/vt-d: Add helper to setup pasid nested translation
iommu/vt-d: Add helper for nested domain allocation
iommu/vt-d: Extend dmar_domain to support nested domain
iommufd: Add data structure for Intel VT-d stage-1 domain allocation
iommu/vt-d: Enhance capability check for nested parent domain allocation
iommufd/selftest: Add coverage for IOMMU_HWPT_ALLOC with nested HWPTs
iommufd/selftest: Add nested domain allocation for mock domain
iommu: Add iommu_copy_struct_from_user helper
iommufd: Add a nested HW pagetable object
iommu: Pass in parent domain with user_data to domain_alloc_user op
iommufd: Share iommufd_hwpt_alloc with IOMMUFD_OBJ_HWPT_NESTED
iommufd: Derive iommufd_hwpt_paging from iommufd_hw_pagetable
...
Diffstat (limited to 'include/uapi')
-rw-r--r-- | include/uapi/linux/iommufd.h | 180 |
1 files changed, 176 insertions, 4 deletions
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index b4ba0c0cbab6..0b2bc6252e2c 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -47,6 +47,8 @@ enum { IOMMUFD_CMD_VFIO_IOAS, IOMMUFD_CMD_HWPT_ALLOC, IOMMUFD_CMD_GET_HW_INFO, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, }; /** @@ -348,19 +350,85 @@ struct iommu_vfio_ioas { #define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) /** + * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation + * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a HWPT that can serve as + * the parent HWPT in a nesting configuration. + * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is + * enforced on device attachment + */ +enum iommufd_hwpt_alloc_flags { + IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, +}; + +/** + * enum iommu_hwpt_vtd_s1_flags - Intel VT-d stage-1 page table + * entry attributes + * @IOMMU_VTD_S1_SRE: Supervisor request + * @IOMMU_VTD_S1_EAFE: Extended access enable + * @IOMMU_VTD_S1_WPE: Write protect enable + */ +enum iommu_hwpt_vtd_s1_flags { + IOMMU_VTD_S1_SRE = 1 << 0, + IOMMU_VTD_S1_EAFE = 1 << 1, + IOMMU_VTD_S1_WPE = 1 << 2, +}; + +/** + * struct iommu_hwpt_vtd_s1 - Intel VT-d stage-1 page table + * info (IOMMU_HWPT_DATA_VTD_S1) + * @flags: Combination of enum iommu_hwpt_vtd_s1_flags + * @pgtbl_addr: The base address of the stage-1 page table. + * @addr_width: The address width of the stage-1 page table + * @__reserved: Must be 0 + */ +struct iommu_hwpt_vtd_s1 { + __aligned_u64 flags; + __aligned_u64 pgtbl_addr; + __u32 addr_width; + __u32 __reserved; +}; + +/** + * enum iommu_hwpt_data_type - IOMMU HWPT Data Type + * @IOMMU_HWPT_DATA_NONE: no data + * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table + */ +enum iommu_hwpt_data_type { + IOMMU_HWPT_DATA_NONE, + IOMMU_HWPT_DATA_VTD_S1, +}; + +/** * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) * @size: sizeof(struct iommu_hwpt_alloc) - * @flags: Must be 0 + * @flags: Combination of enum iommufd_hwpt_alloc_flags * @dev_id: The device to allocate this HWPT for - * @pt_id: The IOAS to connect this HWPT to + * @pt_id: The IOAS or HWPT to connect this HWPT to * @out_hwpt_id: The ID of the new HWPT * @__reserved: Must be 0 + * @data_type: One of enum iommu_hwpt_data_type + * @data_len: Length of the type specific data + * @data_uptr: User pointer to the type specific data * * Explicitly allocate a hardware page table object. This is the same object * type that is returned by iommufd_device_attach() and represents the * underlying iommu driver's iommu_domain kernel object. * - * A HWPT will be created with the IOVA mappings from the given IOAS. + * A kernel-managed HWPT will be created with the mappings from the given + * IOAS via the @pt_id. The @data_type for this allocation must be set to + * IOMMU_HWPT_DATA_NONE. The HWPT can be allocated as a parent HWPT for a + * nesting configuration by passing IOMMU_HWPT_ALLOC_NEST_PARENT via @flags. + * + * A user-managed nested HWPT will be created from a given parent HWPT via + * @pt_id, in which the parent HWPT must be allocated previously via the + * same ioctl from a given IOAS (@pt_id). In this case, the @data_type + * must be set to a pre-defined type corresponding to an I/O page table + * type supported by the underlying IOMMU hardware. + * + * If the @data_type is set to IOMMU_HWPT_DATA_NONE, @data_len and + * @data_uptr should be zero. Otherwise, both @data_len and @data_uptr + * must be given. */ struct iommu_hwpt_alloc { __u32 size; @@ -369,13 +437,26 @@ struct iommu_hwpt_alloc { __u32 pt_id; __u32 out_hwpt_id; __u32 __reserved; + __u32 data_type; + __u32 data_len; + __aligned_u64 data_uptr; }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) /** + * enum iommu_hw_info_vtd_flags - Flags for VT-d hw_info + * @IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17: If set, disallow read-only mappings + * on a nested_parent domain. + * https://www.intel.com/content/www/us/en/content-details/772415/content-details.html + */ +enum iommu_hw_info_vtd_flags { + IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17 = 1 << 0, +}; + +/** * struct iommu_hw_info_vtd - Intel VT-d hardware information * - * @flags: Must be 0 + * @flags: Combination of enum iommu_hw_info_vtd_flags * @__reserved: Must be 0 * * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec @@ -405,6 +486,20 @@ enum iommu_hw_info_type { }; /** + * enum iommufd_hw_capabilities + * @IOMMU_HW_CAP_DIRTY_TRACKING: IOMMU hardware support for dirty tracking + * If available, it means the following APIs + * are supported: + * + * IOMMU_HWPT_GET_DIRTY_BITMAP + * IOMMU_HWPT_SET_DIRTY_TRACKING + * + */ +enum iommufd_hw_capabilities { + IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0, +}; + +/** * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) * @size: sizeof(struct iommu_hw_info) * @flags: Must be 0 @@ -415,6 +510,8 @@ enum iommu_hw_info_type { * the iommu type specific hardware information data * @out_data_type: Output the iommu hardware info type as defined in the enum * iommu_hw_info_type. + * @out_capabilities: Output the generic iommu capability info type as defined + * in the enum iommu_hw_capabilities. * @__reserved: Must be 0 * * Query an iommu type specific hardware information data from an iommu behind @@ -439,6 +536,81 @@ struct iommu_hw_info { __aligned_u64 data_uptr; __u32 out_data_type; __u32 __reserved; + __aligned_u64 out_capabilities; }; #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) + +/* + * enum iommufd_hwpt_set_dirty_tracking_flags - Flags for steering dirty + * tracking + * @IOMMU_HWPT_DIRTY_TRACKING_ENABLE: Enable dirty tracking + */ +enum iommufd_hwpt_set_dirty_tracking_flags { + IOMMU_HWPT_DIRTY_TRACKING_ENABLE = 1, +}; + +/** + * struct iommu_hwpt_set_dirty_tracking - ioctl(IOMMU_HWPT_SET_DIRTY_TRACKING) + * @size: sizeof(struct iommu_hwpt_set_dirty_tracking) + * @flags: Combination of enum iommufd_hwpt_set_dirty_tracking_flags + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @__reserved: Must be 0 + * + * Toggle dirty tracking on an HW pagetable. + */ +struct iommu_hwpt_set_dirty_tracking { + __u32 size; + __u32 flags; + __u32 hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) + +/** + * enum iommufd_hwpt_get_dirty_bitmap_flags - Flags for getting dirty bits + * @IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR: Just read the PTEs without clearing + * any dirty bits metadata. This flag + * can be passed in the expectation + * where the next operation is an unmap + * of the same IOVA range. + * + */ +enum iommufd_hwpt_get_dirty_bitmap_flags { + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR = 1, +}; + +/** + * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP) + * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap) + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @flags: Combination of enum iommufd_hwpt_get_dirty_bitmap_flags + * @__reserved: Must be 0 + * @iova: base IOVA of the bitmap first bit + * @length: IOVA range size + * @page_size: page size granularity of each bit in the bitmap + * @data: bitmap where to set the dirty bits. The bitmap bits each + * represent a page_size which you deviate from an arbitrary iova. + * + * Checking a given IOVA is dirty: + * + * data[(iova / page_size) / 64] & (1ULL << ((iova / page_size) % 64)) + * + * Walk the IOMMU pagetables for a given IOVA range to return a bitmap + * with the dirty IOVAs. In doing so it will also by default clear any + * dirty bit metadata set in the IOPTE. + */ +struct iommu_hwpt_get_dirty_bitmap { + __u32 size; + __u32 hwpt_id; + __u32 flags; + __u32 __reserved; + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 data; +}; +#define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP) + #endif |