Re: [PATCH 2/3] drm/amdkfd: svm unmap use page aligned address

[Philip Yang <yangp@amd.com>]

On 2025-10-02 18:04, Chen, Xiaogang wrote:
>
> On 10/2/2025 12:43 PM, Philip Yang wrote:
>> svm_range_unmap_from_gpus uses page aligned start, end address, the end
>> address is inclusive.
>>
>> Fixes: 38c55f6719f7 ("drm/amdkfd: Handle lack of READ permissions in 
>> SVM mapping")
>> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++--
>>   1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c 
>> b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> index e8a15751c125..742c28833650 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> @@ -1723,8 +1723,8 @@ static int svm_range_validate_and_map(struct 
>> mm_struct *mm,
>>                   svm_range_lock(prange);
>>                   if (vma->vm_flags & VM_WRITE)
>>                       pr_debug("VM_WRITE without VM_READ is not 
>> supported");
>> -                s = max(start, prange->start);
>> -                e = min(end, prange->last);
>> +                s = max(start >> PAGE_SHIFT, prange->start);
>> +                e = min((end - 1) >> PAGE_SHIFT, prange->last);
>
> I think the problem is more than that. Here "end" is the last place 
> for prange gpu mapping and the handling here is for a vma. Should use 
> end of the vma range to get "e".

You are right, end should use next - 1 instead, I will refactor the 
patch series, send out v2.

regards,

Philip

>
> Regards
>
> Xiaogang
>
>>                   if (e >= s)
>>                       r = svm_range_unmap_from_gpus(prange, s, e,
>> KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU);