Re: [PATCH 3/4] drm/xe/svm: Extend MAP range to reduce vma fragmentation

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

On Mon, Sep 22, 2025 at 04:13:15PM +0530, Himal Prasad Ghimiray wrote:
> When DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR is set during VM_BIND_OP_MAP,
> the mapping logic now checks adjacent cpu_addr_mirror VMAs with default
> attributes and expands the mapping range accordingly. This ensures that
> `bo_unmap` operations ideally target the same area and helps reduce
> fragmentation by coalescing nearby compatible VMAs into a single mapping.
> 
> Cc: Matthew Brost <matthew.brost@intel.com>

Reviewed-by: Matthew Brost <matthew.brost@intel.com>

> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_vm.c | 9 +++++++--
>  1 file changed, 7 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index 246bff91fa43..198130f71e0f 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -2213,6 +2213,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>  	struct drm_gpuva_ops *ops;
>  	struct drm_gpuva_op *__op;
>  	struct drm_gpuvm_bo *vm_bo;
> +	u64 range_start = addr;
>  	u64 range_end = addr + range;
>  	int err;
>  
> @@ -2225,10 +2226,14 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>  
>  	switch (operation) {
>  	case DRM_XE_VM_BIND_OP_MAP:
> +		if (flags & DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR)
> +			xe_vm_find_cpu_addr_mirror_vma_range(vm, &range_start, &range_end);
> +
> +		fallthrough;
>  	case DRM_XE_VM_BIND_OP_MAP_USERPTR: {
>  		struct drm_gpuvm_map_req map_req = {
> -			.map.va.addr = addr,
> -			.map.va.range = range,
> +			.map.va.addr = range_start,
> +			.map.va.range = range_end - range_start,
>  			.map.gem.obj = obj,
>  			.map.gem.offset = bo_offset_or_userptr,
>  		};
> -- 
> 2.34.1
>