Re: [RFC 10/29] drm/xe/svm: Refactor usage of drm_gpusvm* function in xe_svm

[Matthew Brost <matthew.brost@intel.com>]

On Fri, Mar 14, 2025 at 01:32:07PM +0530, Himal Prasad Ghimiray wrote:
> Define xe_svm_range_find_or_insert function wrapping
> drm_gpusvm_range_find_or_insert for reusing in prefetch.
> 
> Define xe_svm_range_get_pages function wrapping
> drm_gpusvm_range_get_pages for reusing in prefetch.
> 
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_svm.c | 73 +++++++++++++++++++++++++++++++------
>  drivers/gpu/drm/xe/xe_svm.h | 20 ++++++++++
>  2 files changed, 81 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index 07511011aba6..5a4cb14d608e 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -714,7 +714,6 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
>  			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
>  	};
>  	struct xe_svm_range *range;
> -	struct drm_gpusvm_range *r;
>  	struct drm_exec exec;
>  	struct dma_fence *fence;
>  	ktime_t end = 0;
> @@ -729,13 +728,11 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
>  	if (err)
>  		return err;
>  
> -	r = drm_gpusvm_range_find_or_insert(&vm->svm.gpusvm, fault_addr,
> -					    xe_vma_start(vma), xe_vma_end(vma),
> -					    &ctx);
> -	if (IS_ERR(r))
> -		return PTR_ERR(r);
> +	range = xe_svm_range_find_or_insert(vm, fault_addr, vma);
> +
> +	if (IS_ERR(range))
> +		return PTR_ERR(range);
>  
> -	range = to_xe_range(r);
>  	if (xe_svm_range_is_valid(range, tile))
>  		return 0;
>  
> @@ -757,13 +754,9 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
>  	}
>  
>  	range_debug(range, "GET PAGES");
> -	err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx);
> +	err = xe_svm_range_get_pages(vm, range, &ctx);
>  	/* Corner where CPU mappings have changed */
>  	if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
> -		if (err == -EOPNOTSUPP) {
> -			range_debug(range, "PAGE FAULT - EVICT PAGES");
> -			drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base);
> -		}
>  		drm_dbg(&vm->xe->drm,
>  			"Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
>  			vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
> @@ -842,6 +835,62 @@ int xe_svm_bo_evict(struct xe_bo *bo)
>  	return drm_gpusvm_evict_to_ram(&bo->devmem_allocation);
>  }
>  
> +/**
> + * xe_svm_range_find_or_insert- Find or insert GPU SVM range
> + * @vm: xe_vm pointer
> + * @addr: address for which range needs to be found/inserted
> + * @vma:  Pointer to struct xe_vma which mirrors CPU
> + *
> + * This function finds or inserts a newly allocated a SVM range based on the
> + * address.
> + *
> + * Return: Pointer to the SVM range on success, ERR_PTR() on failure.
> + */
> +struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr,
> +						 struct xe_vma *vma)

I think you want a drm_gpusvm_ctx argument here. It is odd to duplicate
the context locally when the page fault handler has already set one up.

Matt

> +{
> +	struct drm_gpusvm_range *r;
> +
> +	struct drm_gpusvm_ctx ctx = {
> +		.read_only = xe_vma_read_only(vma),
> +		.devmem_possible = IS_DGFX(vm->xe) && IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
> +		.check_pages_threshold = IS_DGFX(vm->xe) &&
> +					 IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
> +	};
> +
> +	r = drm_gpusvm_range_find_or_insert(&vm->svm.gpusvm, max(addr, xe_vma_start(vma)),
> +					    xe_vma_start(vma), xe_vma_end(vma), &ctx);
> +	if (IS_ERR(r))
> +		return ERR_PTR(PTR_ERR(r));
> +
> +	return to_xe_range(r);
> +}
> +
> +/**
> + * xe_svm_range_get_pages() - Get pages for a SVM range
> + * @vm: Pointer to the struct xe_vm
> + * @range: Pointer to the xe SVM range structure
> + * @ctx: GPU SVM context
> + *
> + * This function gets pages for a SVM range and ensures they are mapped for
> + * DMA access. In case of failure with -EOPNOTSUPP, it evicts the range.
> + *
> + * Return: 0 on success, negative error code on failure.
> + */
> +int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
> +			   struct drm_gpusvm_ctx *ctx)
> +{
> +	int err = 0;
> +
> +	err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, &range->base, ctx);
> +	if (err == -EOPNOTSUPP) {
> +		range_debug(range, "PAGE FAULT - EVICT PAGES");
> +		drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base);
> +	}
> +
> +	return err;
> +}
> +
>  #if IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR)
>  static struct drm_pagemap_device_addr
>  xe_drm_pagemap_device_map(struct drm_pagemap *dpagemap,
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> index c8add37614ec..6bb358bf62ad 100644
> --- a/drivers/gpu/drm/xe/xe_svm.h
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -76,6 +76,12 @@ void xe_svm_range_debug(struct xe_svm_range *range, const char *operation);
>  int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
>  		      struct xe_svm_range *range,
>  		      const struct drm_gpusvm_ctx *ctx);
> +
> +struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr,
> +						 struct xe_vma *vma);
> +
> +int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
> +			   struct drm_gpusvm_ctx *ctx);
>  #else
>  static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range)
>  {
> @@ -137,6 +143,20 @@ int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
>  	return 0;
>  }
>  
> +static inline
> +struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr,
> +						 struct xe_vma *vma)
> +{
> +	return ERR_PTR(-EINVAL);
> +}
> +
> +static inline
> +int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
> +			   struct drm_gpusvm_ctx *ctx)
> +{
> +	return -EINVAL;
> +}
> +
>  #endif
>  
>  /**
> -- 
> 2.34.1
>