Re: [PATCH v3 3/4] drm/xe: Bump prefetch BO LRU via GPUSVM devmem callback

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

On 26-09-2026 07:29, Matthew Brost wrote:
> On Fri, Sep 25, 2026 at 06:56:42PM -0700, Matthew Brost wrote:
>> On Tue, Sep 22, 2026 at 10:08:03AM +0530, Himal Prasad Ghimiray wrote:
>>> Add xe_svm_devmem_lru_bump() and set it as drm_gpusvm_ctx.devmem_fn in
>>> the prefetch worker so each backing BO is moved to the LRU tail during
>>> get_pages.
>>>
>>> v2:
>>> - Guard xe_svm_devmem_lru_bump() against foreign device-memory
>>>    allocations before casting to xe_bo: return early when
>>>    devmem_allocation->ops != &dpagemap_devmem_ops. A shared
>>>    device_private_page_owner can hand us another driver's allocation.
>>>    (Matthew Brost / Sashiko AI review)
>>> - Add stub for function (CI)
>>>
>>> v3:
>>> - Guard xe_svm_devmem_lru_bump() body with CONFIG_DRM_XE_PAGEMAP; it
>>>    references dpagemap_devmem_ops and to_xe_bo(), which only exist when
>>>    PAGEMAP is enabled. Fixes the build with GPUSVM=y, PAGEMAP=n.
>>>    (Sashiko AI review)
>>>
>>> Suggested-by: Matthew Brost <matthew.brost@intel.com>
>>> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
>>> ---
>>>   drivers/gpu/drm/xe/xe_svm.c | 30 ++++++++++++++++++++++++++++++
>>>   drivers/gpu/drm/xe/xe_svm.h |  7 +++++++
>>>   drivers/gpu/drm/xe/xe_vm.c  |  1 +
>>>   3 files changed, 38 insertions(+)
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
>>> index f39e647512ad..018836ecbb06 100644
>>> --- a/drivers/gpu/drm/xe/xe_svm.c
>>> +++ b/drivers/gpu/drm/xe/xe_svm.c
>>> @@ -9,6 +9,7 @@
>>>   #include <drm/drm_managed.h>
>>>   #include <drm/drm_pagemap.h>
>>>   #include <drm/drm_pagemap_util.h>
>>> +#include <drm/ttm/ttm_bo.h>
>>>   
>>>   #include "xe_bo.h"
>>>   #include "xe_exec_queue_types.h"
>>> @@ -1625,6 +1626,35 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
>>>   	return err;
>>>   }
>>>   
>>> +/**
>>> + * xe_svm_devmem_lru_bump() - Move a range's backing BO to the TTM LRU tail
>>> + * @devmem_allocation: The device-memory allocation backing the range's pages
>>> + *
>>> + * Intended as a &drm_gpusvm_ctx.devmem_fn. Runs under the GPUSVM notifier lock;
>>> + * the dma-resv trylock avoids inverting against eviction/shrinker, which take
>>> + * dma-resv before the notifier lock. A contended BO is simply skipped.
>>
>> This kernel doc isn't right.
>>
>> - get_pages() calls ctx.devmem_fn under the notifier
>> - the notifier lock is path of reclaim so dma-resv can't be taken under
>>    the notifier lock
> 
> s/can't be taken under/can't be taken with blocking under/
> 
> Matt

Will fix the kernel doc.
> 
>> - dma-resv also is an outer lock of the notifier when memory is
>>    allocated + migrated
>> - in practice because BO is private (dedicated dma-resv) a trylock
>>    should always work unless it moving elsewhere, e.g., eviction
>>
>> Somehow tie this all together into a coherent kernel doc.
>>
>>> + *
>>> + * A shared device_private_page_owner can hand us allocations backed by a
>>> + * foreign driver; skip anything that is not an xe BO before casting.
>>
>> s/xe/Xe
>>
>> Otherwise LGTM.
>>
>> Matt
>>
>>> + */
>>> +void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation)
>>> +{
>>> +#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
>>> +	struct xe_bo *bo;
>>> +
>>> +	if (devmem_allocation->ops != &dpagemap_devmem_ops)
>>> +		return;
>>> +
>>> +	bo = to_xe_bo(devmem_allocation);
>>> +
>>> +	if (!dma_resv_trylock(bo->ttm.base.resv))
>>> +		return;
>>> +
>>> +	ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);
>>> +	dma_resv_unlock(bo->ttm.base.resv);
>>> +#endif
>>> +}
>>> +
>>>   /**
>>>    * xe_svm_ranges_zap_ptes_in_range - clear ptes of svm ranges in input range
>>>    * @vm: Pointer to the xe_vm structure
>>> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
>>> index 2ef4ef026ccd..585ad64b672b 100644
>>> --- a/drivers/gpu/drm/xe/xe_svm.h
>>> +++ b/drivers/gpu/drm/xe/xe_svm.h
>>> @@ -128,6 +128,8 @@ struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr,
>>>   int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
>>>   			   struct drm_gpusvm_ctx *ctx);
>>>   
>>> +void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation);
>>> +
>>>   bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vma *vma,
>>>   					const struct drm_pagemap *dpagemap);
>>>   
>>> @@ -356,6 +358,11 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
>>>   	return -EINVAL;
>>>   }
>>>   
>>> +static inline
>>> +void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation)
>>> +{
>>> +}
>>> +
>>>   static inline struct xe_svm_range *to_xe_range(struct drm_gpusvm_range *r)
>>>   {
>>>   	return NULL;
>>> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>>> index 6b793ef31537..0fdc740f1a41 100644
>>> --- a/drivers/gpu/drm/xe/xe_vm.c
>>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>>> @@ -3260,6 +3260,7 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_ops *vops,
>>>   	ctx.devmem_possible = devmem_possible;
>>>   	ctx.check_pages_threshold = devmem_possible ? SZ_64K : 0;
>>>   	ctx.device_private_page_owner = xe_svm_private_page_owner(vm, !dpagemap);
>>> +	ctx.devmem_fn = xe_svm_devmem_lru_bump;
>>>   
>>>   	skip_threads =  op->prefetch_range.ranges_count == 1 ||
>>>   		(!dpagemap && !(vops->flags &
>>> -- 
>>> 2.43.0
>>>