lkml.org 
[lkml]   [2023]   [Sep]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH v5 07/11] iommufd: Add data structure for Intel VT-d stage-1 cache invalidation
From
On 2023/9/21 21:33, Baolu Lu wrote:
> On 2023/9/21 15:54, Yi Liu wrote:
>> This adds the data structure for flushing iotlb for the nested domain
>> allocated with IOMMU_HWPT_TYPE_VTD_S1 type.
>>
>> This only supports invalidating IOTLB, but no for device-TLB as device-TLB
>> invalidation will be covered automatically in the IOTLB invalidation if the
>> underlying IOMMU driver has enabled ATS for the affected device.
>>
>> Signed-off-by: Yi Liu <yi.l.liu@intel.com>
>> ---
>>   include/uapi/linux/iommufd.h | 34 ++++++++++++++++++++++++++++++++++
>>   1 file changed, 34 insertions(+)
>>
>> diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
>> index 18a502e206c3..3050efbceb57 100644
>> --- a/include/uapi/linux/iommufd.h
>> +++ b/include/uapi/linux/iommufd.h
>> @@ -510,6 +510,40 @@ struct iommu_hw_info {
>>   };
>>   #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
>> +/**
>> + * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d
>> + *                                           stage-1 cache invalidation
>> + * @IOMMU_VTD_QI_FLAGS_LEAF: The LEAF flag indicates whether only the
>> + *                           leaf PTE caching needs to be invalidated
>> + *                           and other paging structure caches can be
>> + *                           preserved.
>> + */
>> +enum iommu_hwpt_vtd_s1_invalidate_flags {
>> +    IOMMU_VTD_QI_FLAGS_LEAF = 1 << 0,
>> +};
>> +
>> +/**
>> + * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation
>> + *                                       (IOMMU_HWPT_TYPE_VTD_S1)
>> + * @addr: The start address of the addresses to be invalidated.
>
> Is there an alignment requirement for @addr? If so, is 4K alignment
> sufficient? Perhaps we need to document it here so that user space can
> calculate the @addr correctly.

yes, it should be aligned. let's document it in the kdoc.

>
>> + * @npages: Number of contiguous 4K pages to be invalidated.
>> + * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags
>> + * @__reserved: Must be 0
>> + *
>> + * The Intel VT-d specific invalidation data for user-managed stage-1 cache
>> + * invalidation under nested translation. Userspace uses this structure to
>> + * tell host about the impacted caches after modifying the stage-1 page
>> table.
>> + *
>> + * Invalidating all the caches related to the page table by setting @addr
>> + * to be 0 and @npages to be __aligned_u64(-1).
>> + */
>> +struct iommu_hwpt_vtd_s1_invalidate {
>> +    __aligned_u64 addr;
>> +    __aligned_u64 npages;
>> +    __u32 flags;
>> +    __u32 __reserved;
>> +};
>> +
>>   /**
>>    * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
>>    * @size: sizeof(struct iommu_hwpt_invalidate)
>
> Best regards,
> baolu

--
Regards,
Yi Liu

\
 
 \ /
  Last update: 2023-09-25 08:55    [W:0.067 / U:0.964 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site