Re: [PATCH v3 09/19] drm/xe/svm: Split system allocator vma incase of madvise call

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

On 29-05-2025 08:19, Matthew Brost wrote:
> On Tue, May 27, 2025 at 10:09:53PM +0530, Himal Prasad Ghimiray wrote:
>> If the start or end of input address range lies within system allocator
>> vma split the vma to create new vma's as per input range.
>>
>> v2 (Matthew Brost)
>> - Add lockdep_assert_write for vm->lock
>> - Remove unnecessary page aligned checks
>> - Add kerrnel-doc and comments
>> - Remove unnecessary unwind_ops and return
>> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_vm.c | 95 ++++++++++++++++++++++++++++++++++++++
>>   drivers/gpu/drm/xe/xe_vm.h |  2 +
>>   2 files changed, 97 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>> index d60b711e97e9..c220bf904ee0 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.c
>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>> @@ -4161,3 +4161,98 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap)
>>   	}
>>   	kvfree(snap);
>>   }
>> +
>> +/**
>> + * xe_vm_alloc_madvise_vma - Allocate VMA's with madvise ops
>> + * @vm: Pointer to the xe_vm structure
>> + * @start: Starting input address
>> + * @range: Size of the input range
>> + *
>> + * This function splits existing vma to create new vma for user provided input range
>> + *
>> + *  Return: 0 if success
>> + */
>> +int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
>> +{
>> +	struct xe_vma_ops vops;
>> +	struct drm_gpuva_ops *ops = NULL;
>> +	struct drm_gpuva_op *__op;
>> +	bool is_cpu_addr_mirror = false;
>> +	int err;
>> +
>> +	vm_dbg(&vm->xe->drm, "MADVISE IN: addr=0x%016llx, size=0x%016llx", start, range);
>> +
>> +	lockdep_assert_held_write(&vm->lock);
>> +
>> +	vm_dbg(&vm->xe->drm, "MADVISE_OPS_CREATE: addr=0x%016llx, size=0x%016llx", start, range);
>> +	ops = drm_gpuvm_sm_map_ops_create(&vm->gpuvm, start, range,
>> +					  DRM_GPUVM_SKIP_GEM_OBJ_VA_SPLIT_MADVISE,
>> +					  NULL, start);
>> +	if (IS_ERR(ops))
>> +		return PTR_ERR(ops);
>> +
>> +	if (list_empty(&ops->list)) {
>> +		err = 0;
>> +		goto free_ops;
>> +	}
>> +
>> +	drm_gpuva_for_each_op(__op, ops) {
>> +		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
>> +
>> +		if (__op->op == DRM_GPUVA_OP_REMAP) {
>> +			if (xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.remap.unmap->va)))
>> +				is_cpu_addr_mirror = true;
>> +			else
>> +				is_cpu_addr_mirror = false;
> 
> Maybe let's add a sanity check here to make sure we know what we are
> doing.

Sounds good.>
> 			xe_assert(xe, !remap_op);
> 			remap_op = true;
>> +		}
>> +
>> +		if (__op->op == DRM_GPUVA_OP_MAP)
>> +			/* In case of madvise ops DRM_GPUVA_OP_REMAP is always by
>> +			 * DRM_GPUVA_OP_REMAP, so ensure we assign op->map.is_cpu_addr_mirror true
>> +			 * if REMAP is for xe_vma_is_cpu_addr_mirror vma
>> +			 */
>> +			op->map.is_cpu_addr_mirror = is_cpu_addr_mirror;
> 
> 			xe_assert(xe, remap_op);
> 
>> +
>> +		print_op(vm->xe, __op);
>> +	}
>> +
>> +	xe_vma_ops_init(&vops, vm, NULL, NULL, 0);
>> +	err = vm_bind_ioctl_ops_parse(vm, ops, &vops);
>> +	if (err)
>> +		goto unwind_ops;
>> +
>> +	xe_vm_lock(vm, false);
>> +
>> +	drm_gpuva_for_each_op(__op, ops) {
>> +		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
>> +		struct xe_vma *vma;
>> +		struct xe_vma_mem_attr temp_attr;
>> +
>> +		if (__op->op == DRM_GPUVA_OP_UNMAP) {
>> +			/* There should be no unmap */
>> +			XE_WARN_ON("UNEXPECTED UNMAP");
>> +			xe_vma_destroy(gpuva_to_vma(op->base.unmap.va), NULL);
>> +		} else if (__op->op == DRM_GPUVA_OP_REMAP) {
>> +			vma = gpuva_to_vma(op->base.remap.unmap->va);
>> +			/* Store attributes for REMAP UNMAPPED VMA, so they can be assigned
>> +			 * to newly MAPPED vma.
>> +			 */
>> +			cp_vma_mem_attr(&temp_attr, &vma->attr);
> 
> Again maybe drop the helper here.

Sure.

> 
>> +			xe_vma_destroy(gpuva_to_vma(op->base.remap.unmap->va), NULL);
>> +		} else if (__op->op == DRM_GPUVA_OP_MAP) {
>> +			vma = op->map.vma;
>> +			cp_vma_mem_attr(&vma->attr, &temp_attr);
> 
> And here.
> 
> With the nits fixed:
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>

Thanks

> 
>> +		}
>> +	}
>> +
>> +	xe_vm_unlock(vm);
>> +	drm_gpuva_ops_free(&vm->gpuvm, ops);
>> +	return 0;
>> +
>> +unwind_ops:
>> +	vm_bind_ioctl_ops_unwind(vm, &ops, 1);
>> +free_ops:
>> +	if (ops)
>> +		drm_gpuva_ops_free(&vm->gpuvm, ops);
>> +	return err;
>> +}
>> diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
>> index 1ef98113fa5b..8151b1b01a13 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.h
>> +++ b/drivers/gpu/drm/xe/xe_vm.h
>> @@ -171,6 +171,8 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
>>   
>>   struct xe_vma *xe_vm_find_vma_by_addr(struct xe_vm *vm, u64 page_addr);
>>   
>> +int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t addr, uint64_t size);
>> +
>>   /**
>>    * to_userptr_vma() - Return a pointer to an embedding userptr vma
>>    * @vma: Pointer to the embedded struct xe_vma
>> -- 
>> 2.34.1
>>