Re: [PATCH v6 19/20] drm/xe/svm: Implement prefetch support for SVM ranges

["Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>]

On 02-05-2025 19:12, Thomas Hellström wrote:
> On Wed, 2025-04-30 at 17:49 +0530, Himal Prasad Ghimiray wrote:
>> This commit adds prefetch support for SVM ranges, utilizing the
>> existing ioctl vm_bind functionality to achieve this.
>>
>> v2: rebase
>>
>> v3:
>>     - use xa_for_each() instead of manual loop
>>     - check range is valid and in preferred location before adding to
>>       xarray
>>     - Fix naming conventions
>>     - Fix return condition as -ENODATA instead of -EAGAIN (Matthew
>> Brost)
>>     - Handle sparsely populated cpu vma range (Matthew Brost)
>>
>> v4:
>>     - fix end address to find next cpu vma in case of -ENOENT
>>
>> v5:
>>     - Move find next vma logic to drm gpusvm layer
>>     - Avoid mixing declaration and logic
>>
>> v6:
>>    - Use new function names
>>    - Move eviction logic to prefetch_ranges
>>
>> Cc: Matthew Brost <matthew.brost@intel.com>
>> Signed-off-by: Himal Prasad Ghimiray
>> <himal.prasad.ghimiray@intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_pt.c |  58 ++++++++---
>>   drivers/gpu/drm/xe/xe_vm.c | 197
>> +++++++++++++++++++++++++++++++++++--
>>   2 files changed, 234 insertions(+), 21 deletions(-)
>>
> 
> I was thinking a bit around the UAPI, and prefetching foreign device
> regions. That doesn't really fit into the current UAPI.
> 
> What are your thoughts here. IMO this should align somewhat to what we
> do for madvise().
> 
> Let's say we want to prefetch into a foreign device memory region
> identified by an fd? I figure we could add that later as an extension.
> 
> But how does the UMD API for this look? Do we cover current usage with
> the existing UAPI syntax?

During Initial discussions one of the way we discussed was using a flag 
something like DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC for prefetch to 
madvise assigned preferred location.

so it will be two step process from UMD perspective:
1) madvise sets up preferred location: which should also be used in 
pagefault handler.

2) If user wants to prefetch to same location, user passes region as 
DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC to vm_bind ioctl.

https://patchwork.freedesktop.org/patch/647180/?series=146290&rev=4

or we can simply pass u32 devmem_fd as prefetch_mem_region_instance to 
vm_bind ioctl, if we want it to be single step, but w/o madvise that 
wont work for pf handler.

/Himal>
> /Thomas
>