[PATCH v7 00/24] MADVISE FOR XE

[Ghimiray, Himal Prasad]

On 14-08-2025 16:29, Himal Prasad Ghimiray wrote:
> -v8
> Define new function in gpuvm for madvise
> Fix tile check in ops_create
> 
> -v7
> Change gpuvm layering on gpuvm_map_req struct
> Fix EAGAIN return on garbage collector splitting vma
> 
> -v6
> Rebase on gpuvm patches
> Address review comments
> 
> -v5
> Restore attributes to default after free from userspace
> Add defragment worker to merge cpu mirror vma with default attributes
> Avoid using VMA in uapi
> address review comments
> 
> -v4:
> fix atomic policies
> fix attribute copy
> address review comments
> 
> Provides a user API to assign attributes like pat_index, atomic
> operation type, and preferred location for SVM ranges.
> The Kernel Mode Driver (KMD) may split existing VMAs to cover input
> ranges, assign user-provided attributes, and invalidate existing PTEs so
> that the next page fault/prefetch can use the new attributes.

Implementation is tested with 
https://github.com/intel/compute-runtime/pull/845

> 
> Boris Brezillon (2):
>    drm/gpuvm: Pass map arguments through a struct
>    drm/gpuvm: Kill drm_gpuva_init()
> 
> Himal Prasad Ghimiray (22):
>    drm/gpuvm: Introduce drm_gpuvm_madvise_ops_create
>    drm/xe/uapi: Add madvise interface
>    drm/xe/vm: Add attributes struct as member of vma
>    drm/xe/vma: Move pat_index to vma attributes
>    drm/xe/vma: Modify new_vma to accept struct xe_vma_mem_attr as
>      parameter
>    drm/gpusvm: Make drm_gpusvm_for_each_* macros public
>    drm/xe/svm: Split system allocator vma incase of madvise call
>    drm/xe: Allow CPU address mirror VMA unbind with gpu bindings for
>      madvise
>    drm/xe/svm: Add xe_svm_ranges_zap_ptes_in_range() for PTE zapping
>    drm/xe: Implement madvise ioctl for xe
>    drm/xe/svm: Add svm ranges migration policy on atomic access
>    drm/xe/madvise: Update migration policy based on preferred location
>    drm/xe/svm: Support DRM_XE_SVM_MEM_RANGE_ATTR_PAT memory attribute
>    drm/xe/uapi: Add flag for consulting madvise hints on svm prefetch
>    drm/xe/svm: Consult madvise preferred location in prefetch
>    drm/xe/bo: Add attributes field to xe_bo
>    drm/xe/bo: Update atomic_access attribute on madvise
>    drm/xe/madvise: Skip vma invalidation if mem attr are unchanged
>    drm/xe/vm: Add helper to check for default VMA memory attributes
>    drm/xe: Reset VMA attributes to default in SVM garbage collector
>    drm/xe: Enable madvise ioctl for xe
>    drm/xe/uapi: Add UAPI for querying VMA count and memory attributes
> 
>   drivers/gpu/drm/drm_gpusvm.c           | 122 ++-----
>   drivers/gpu/drm/drm_gpuvm.c            | 287 ++++++++++++----
>   drivers/gpu/drm/imagination/pvr_vm.c   |  15 +-
>   drivers/gpu/drm/msm/msm_gem_vma.c      |  33 +-
>   drivers/gpu/drm/nouveau/nouveau_uvmm.c |  11 +-
>   drivers/gpu/drm/panthor/panthor_mmu.c  |  13 +-
>   drivers/gpu/drm/xe/Makefile            |   1 +
>   drivers/gpu/drm/xe/xe_bo.c             |  29 +-
>   drivers/gpu/drm/xe/xe_bo_types.h       |   8 +
>   drivers/gpu/drm/xe/xe_device.c         |   4 +
>   drivers/gpu/drm/xe/xe_gt_pagefault.c   |  35 +-
>   drivers/gpu/drm/xe/xe_pt.c             |  39 ++-
>   drivers/gpu/drm/xe/xe_svm.c            | 254 ++++++++++++--
>   drivers/gpu/drm/xe/xe_svm.h            |  23 ++
>   drivers/gpu/drm/xe/xe_vm.c             | 438 ++++++++++++++++++++++--
>   drivers/gpu/drm/xe/xe_vm.h             |  10 +-
>   drivers/gpu/drm/xe/xe_vm_madvise.c     | 445 +++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_vm_madvise.h     |  15 +
>   drivers/gpu/drm/xe/xe_vm_types.h       |  57 +++-
>   include/drm/drm_gpusvm.h               |  70 ++++
>   include/drm/drm_gpuvm.h                |  38 ++-
>   include/uapi/drm/xe_drm.h              | 274 +++++++++++++++
>   22 files changed, 1922 insertions(+), 299 deletions(-)
>   create mode 100644 drivers/gpu/drm/xe/xe_vm_madvise.c
>   create mode 100644 drivers/gpu/drm/xe/xe_vm_madvise.h
>