Re: [RFC 13/29] drm/gpuvm: Introduce MADVISE Operations

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

On 14-03-2025 13:32, Himal Prasad Ghimiray wrote:
> Introduce MADVISE operations that do not unmap the GPU VMA. These
> operations split VMAs if the start or end addresses fall within existing
> VMAs. The operations can create up to 2 REMAPS and 2 MAPs.
> 
> If the input range is within the existing range, it creates REMAP:UNMAP,
> REMAP:PREV, REMAP:NEXT, and MAP operations for the input range.
>    Example:
>    Input Range: 0x00007f0a54000000 to 0x00007f0a54400000
>    GPU VMA: 0x0000000000000000 to 0x0000800000000000
>    Operations Result:
>    - REMAP:UNMAP: addr=0x0000000000000000, range=0x0000800000000000
>    - REMAP:PREV: addr=0x0000000000000000, range=0x00007f0a54000000
>    - REMAP:NEXT: addr=0x00007f0a54400000, range=0x000000f5abc00000
>    - MAP: addr=0x00007f0a54000000, range=0x0000000000400000
> 
> If the input range starts at the beginning of one GPU VMA and ends at
> the end of another VMA, covering multiple VMAs, the operations do nothing.
>    Example:
>    Input Range: 0x00007fc898800000 to 0x00007fc899000000
>    GPU VMAs:
>    - 0x0000000000000000 to 0x00007fc898800000
>    - 0x00007fc898800000 to 0x00007fc898a00000
>    - 0x00007fc898a00000 to 0x00007fc898c00000
>    - 0x00007fc898c00000 to 0x00007fc899000000
>    - 0x00007fc899000000 to 0x00007fc899200000
>    Operations Result: None
> 
> Cc: Danilo Krummrich <dakr@redhat.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> ---
>   drivers/gpu/drm/drm_gpuvm.c | 175 +++++++++++++++++++++++++++++++++++-
>   include/drm/drm_gpuvm.h     |   6 ++
>   2 files changed, 180 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
> index f9eb56f24bef..904a26641b21 100644
> --- a/drivers/gpu/drm/drm_gpuvm.c
> +++ b/drivers/gpu/drm/drm_gpuvm.c
> @@ -2230,7 +2230,7 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm,
>   				ret = op_remap_cb(ops, priv, NULL, &n, &u);
>   				if (ret)
>   					return ret;
> -				break;
> +				return 0;

 > -				break;
 > +				return 0;

Incorrectly left in patch, ignore this part.

>   			}
>   		}
>   	}
> @@ -2240,6 +2240,143 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm,
>   			 req_obj, req_offset);
>   }
>   
> +static int
> +__drm_gpuvm_skip_split_map(struct drm_gpuvm *gpuvm,
> +			   const struct drm_gpuvm_ops *ops, void *priv,
> +			   u64 req_addr, u64 req_range,
> +			   bool skip_gem_obj_va, u64 req_offset)
> +{
> +	struct drm_gpuva *va, *next;
> +	u64 req_end = req_addr + req_range;
> +	int ret;
> +
> +	if (unlikely(!drm_gpuvm_range_valid(gpuvm, req_addr, req_range)))
> +		return -EINVAL;
> +
> +	drm_gpuvm_for_each_va_range_safe(va, next, gpuvm, req_addr, req_end) {
> +		struct drm_gem_object *obj = va->gem.obj;
> +		u64 offset = va->gem.offset;
> +		u64 addr = va->va.addr;
> +		u64 range = va->va.range;
> +		u64 end = addr + range;
> +
> +		if (addr == req_addr) {
> +			if (end == req_end)
> +				return 0;
> +
> +			if (end < req_end)
> +				continue;
> +
> +			if (end > req_end) {
> +				if (skip_gem_obj_va && !!obj)
> +					return 0;
> +
> +				struct drm_gpuva_op_map n = {
> +					.va.addr = req_end,
> +					.va.range = range - req_range,
> +					.gem.obj = obj,
> +					.gem.offset = offset + req_range,
> +				};
> +				struct drm_gpuva_op_unmap u = {
> +					.va = va,
> +					.keep = false,
> +				};
> +
> +				ret = op_remap_cb(ops, priv, NULL, &n, &u);
> +				if (ret)
> +					return ret;
> +
> +				break;
> +			}
> +		} else if (addr < req_addr) {
> +			u64 ls_range = req_addr - addr;
> +			struct drm_gpuva_op_map p = {
> +				.va.addr = addr,
> +				.va.range = ls_range,
> +				.gem.obj = obj,
> +				.gem.offset = offset,
> +			};
> +			struct drm_gpuva_op_unmap u = { .va = va, .keep = false, };
> +
> +			if (end == req_end) {
> +				if (skip_gem_obj_va && !!obj)
> +					return 0;
> +
> +				ret = op_remap_cb(ops, priv, &p, NULL, &u);
> +				if (ret)
> +					return ret;
> +				break;
> +			}
> +
> +			if (end < req_end) {
> +				if (skip_gem_obj_va && !!obj)
> +					continue;
> +
> +				ret = op_remap_cb(ops, priv, &p, NULL, &u);
> +				if (ret)
> +					return ret;
> +
> +				ret = op_map_cb(ops, priv, req_addr,
> +						min(end - req_addr, req_end - end),
> +						NULL, req_offset);
> +				if (ret)
> +					return ret;
> +				continue;
> +			}
> +
> +			if (end > req_end) {
> +				if (skip_gem_obj_va && !!obj)
> +					return 0;
> +
> +				struct drm_gpuva_op_map n = {
> +					.va.addr = req_end,
> +					.va.range = end - req_end,
> +					.gem.obj = obj,
> +					.gem.offset = offset + ls_range +
> +						      req_range,
> +				};
> +
> +				ret = op_remap_cb(ops, priv, &p, &n, &u);
> +				if (ret)
> +					return ret;
> +				break;
> +			}
> +		} else if (addr > req_addr) {
> +			if (end == req_end)
> +				return 0;
> +
> +			if (end < req_end)
> +				continue;
> +
> +			if (end > req_end) {
> +				if (skip_gem_obj_va && !!obj)
> +					return 0;
> +
> +				struct drm_gpuva_op_map n = {
> +					.va.addr = req_end,
> +					.va.range = end - req_end,
> +					.gem.obj = obj,
> +					.gem.offset = offset + req_end - addr,
> +				};
> +				struct drm_gpuva_op_unmap u = {
> +					.va = va,
> +					.keep = false,
> +				};
> +
> +				ret = op_remap_cb(ops, priv, NULL, &n, &u);
> +				if (ret)
> +					return ret;
> +				return op_map_cb(ops, priv, addr,
> +						 (req_end - addr), NULL, req_offset);
> +			}
> +		}
> +	}
> +
> +	return op_map_cb(ops, priv,
> +			 req_addr, req_range,
> +			 NULL, req_offset);
> +}
> +
>   static int
>   __drm_gpuvm_sm_unmap(struct drm_gpuvm *gpuvm,
>   		     const struct drm_gpuvm_ops *ops, void *priv,
> @@ -2548,6 +2685,42 @@ drm_gpuvm_sm_map_ops_create(struct drm_gpuvm *gpuvm,
>   }
>   EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map_ops_create);
>   
> +struct drm_gpuva_ops *
> +drm_gpuvm_madvise_ops_create(struct drm_gpuvm *gpuvm,
> +			     u64 req_addr, u64 req_range,
> +			     bool skip_gem_obj_va, u64 req_offset)
> +{
> +	struct drm_gpuva_ops *ops;
> +	struct {
> +		struct drm_gpuvm *vm;
> +		struct drm_gpuva_ops *ops;
> +	} args;
> +	int ret;
> +
> +	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
> +	if (unlikely(!ops))
> +		return ERR_PTR(-ENOMEM);
> +
> +	INIT_LIST_HEAD(&ops->list);
> +
> +	args.vm = gpuvm;
> +	args.ops = ops;
> +
> +	ret = __drm_gpuvm_skip_split_map(gpuvm, &gpuvm_list_ops, &args,
> +					 req_addr, req_range,
> +					 skip_gem_obj_va, req_offset);
> +
> +	if (ret || list_empty(&ops->list))
> +		goto err_free_ops;
> +
> +	return ops;
> +
> +err_free_ops:
> +	drm_gpuva_ops_free(gpuvm, ops);
> +	return ERR_PTR(ret);
> +}
> +EXPORT_SYMBOL_GPL(drm_gpuvm_madvise_ops_create);
> +
>   /**
>    * drm_gpuvm_sm_unmap_ops_create() - creates the &drm_gpuva_ops to split on
>    * unmap
> diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
> index 2a9629377633..e521ebabab9e 100644
> --- a/include/drm/drm_gpuvm.h
> +++ b/include/drm/drm_gpuvm.h
> @@ -1062,6 +1062,12 @@ struct drm_gpuva_ops *
>   drm_gpuvm_sm_map_ops_create(struct drm_gpuvm *gpuvm,
>   			    u64 addr, u64 range,
>   			    struct drm_gem_object *obj, u64 offset);
> +
> +struct drm_gpuva_ops *
> +drm_gpuvm_madvise_ops_create(struct drm_gpuvm *gpuvm,
> +			     u64 addr, u64 range,
> +			     bool skip_gem_obj_va, u64 offset);
> +
>   struct drm_gpuva_ops *
>   drm_gpuvm_sm_unmap_ops_create(struct drm_gpuvm *gpuvm,
>   			      u64 addr, u64 range);