Re: [PATCH v2 (not really v2)] drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset

[Daniel Vetter <daniel@ffwll.ch>]

On Thu, Oct 01, 2015 at 01:33:57PM +0100, Michel Thierry wrote:
> There are some allocations that must be only referenced by 32-bit
> offsets. To limit the chances of having the first 4GB already full,
> objects not requiring this workaround use DRM_MM_SEARCH_BELOW/
> DRM_MM_CREATE_TOP flags
> 
> In specific, any resource used with flat/heapless (0x00000000-0xfffff000)
> General State Heap (GSH) or Instruction State Heap (ISH) must be in a
> 32-bit range, because the General State Offset and Instruction State
> Offset are limited to 32-bits.
> 
> Objects must have EXEC_OBJECT_SUPPORTS_48B_ADDRESS flag to indicate if
> they can be allocated above the 32-bit address range. To limit the
> chances of having the first 4GB already full, objects will use
> DRM_MM_SEARCH_BELOW + DRM_MM_CREATE_TOP flags when possible.
> 
> The libdrm user of the EXEC_OBJECT_SUPPORTS_48B_ADDRESS flag is here:
> http://lists.freedesktop.org/archives/intel-gfx/2015-September/075836.html
> 
> v2: Changed flag logic from neeeds_32b, to supports_48b.
> v3: Moved 48-bit support flag back to exec_object. (Chris, Daniel)
> v4: Split pin flags into PIN_ZONE_4G and PIN_HIGH; update PIN_OFFSET_MASK
> to use last PIN_ defined instead of hard-coded value; use correct limit
> check in eb_vma_misplaced. (Chris)
> v5: Don't touch PIN_OFFSET_MASK and update workaround comment (Chris)
> v6: Apply pin-high for ggtt too (Chris)
> v7: Handle simultaneous pin-high and pin-mappable end correctly (Akash)
>     Fix check for entries currently using +4GB addresses, use min_t and
>     other polish in object_bind_to_vm (Chris)
> v8: Commit message updated to point to libdrm patch.
> v9: vmas are allocated in the correct ozone, so only check flag when the
>     vma has not been allocated. (Chris)
> 
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> (v4)
> Signed-off-by: Michel Thierry <michel.thierry@intel.com>

Queued for -next, thanks for the patch.
-Daniel

> ---
>  drivers/gpu/drm/i915/i915_drv.h            |  2 ++
>  drivers/gpu/drm/i915/i915_gem.c            | 25 +++++++++++++++++++------
>  drivers/gpu/drm/i915/i915_gem_execbuffer.c | 11 +++++++++++
>  include/uapi/drm/i915_drm.h                |  3 ++-
>  4 files changed, 34 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 04d710f..ecc56fa 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2826,6 +2826,8 @@ void i915_gem_vma_destroy(struct i915_vma *vma);
>  #define PIN_OFFSET_BIAS	(1<<3)
>  #define PIN_USER	(1<<4)
>  #define PIN_UPDATE	(1<<5)
> +#define PIN_ZONE_4G	(1<<6)
> +#define PIN_HIGH	(1<<7)
>  #define PIN_OFFSET_MASK (~4095)
>  int __must_check
>  i915_gem_object_pin(struct drm_i915_gem_object *obj,
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index bf5ef7a..f0cfbb9 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -3354,11 +3354,9 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
>  	struct drm_device *dev = obj->base.dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	u32 fence_alignment, unfenced_alignment;
> +	u32 search_flag, alloc_flag;
> +	u64 start, end;
>  	u64 size, fence_size;
> -	u64 start =
> -		flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
> -	u64 end =
> -		flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
>  	struct i915_vma *vma;
>  	int ret;
>  
> @@ -3398,6 +3396,13 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
>  		size = flags & PIN_MAPPABLE ? fence_size : obj->base.size;
>  	}
>  
> +	start = flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
> +	end = vm->total;
> +	if (flags & PIN_MAPPABLE)
> +		end = min_t(u64, end, dev_priv->gtt.mappable_end);
> +	if (flags & PIN_ZONE_4G)
> +		end = min_t(u64, end, (1ULL << 32));
> +
>  	if (alignment == 0)
>  		alignment = flags & PIN_MAPPABLE ? fence_alignment :
>  						unfenced_alignment;
> @@ -3433,13 +3438,21 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
>  	if (IS_ERR(vma))
>  		goto err_unpin;
>  
> +	if (flags & PIN_HIGH) {
> +		search_flag = DRM_MM_SEARCH_BELOW;
> +		alloc_flag = DRM_MM_CREATE_TOP;
> +	} else {
> +		search_flag = DRM_MM_SEARCH_DEFAULT;
> +		alloc_flag = DRM_MM_CREATE_DEFAULT;
> +	}
> +
>  search_free:
>  	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
>  						  size, alignment,
>  						  obj->cache_level,
>  						  start, end,
> -						  DRM_MM_SEARCH_DEFAULT,
> -						  DRM_MM_CREATE_DEFAULT);
> +						  search_flag,
> +						  alloc_flag);
>  	if (ret) {
>  		ret = i915_gem_evict_something(dev, vm, size, alignment,
>  					       obj->cache_level,
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 67ef118..edc17be 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -590,10 +590,17 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
>  		flags |= PIN_GLOBAL;
>  
>  	if (!drm_mm_node_allocated(&vma->node)) {
> +		/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
> +		 * limit address to the first 4GBs for unflagged objects.
> +		 */
> +		if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0)
> +			flags |= PIN_ZONE_4G;
>  		if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
>  			flags |= PIN_GLOBAL | PIN_MAPPABLE;
>  		if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
>  			flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
> +		if ((flags & PIN_MAPPABLE) == 0)
> +			flags |= PIN_HIGH;
>  	}
>  
>  	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags);
> @@ -671,6 +678,10 @@ eb_vma_misplaced(struct i915_vma *vma)
>  	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
>  		return !only_mappable_for_reloc(entry->flags);
>  
> +	if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0 &&
> +	    (vma->node.start + vma->node.size - 1) >> 32)
> +		return true;
> +
>  	return false;
>  }
>  
> diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
> index fd5aa47..484a9fb 100644
> --- a/include/uapi/drm/i915_drm.h
> +++ b/include/uapi/drm/i915_drm.h
> @@ -690,7 +690,8 @@ struct drm_i915_gem_exec_object2 {
>  #define EXEC_OBJECT_NEEDS_FENCE (1<<0)
>  #define EXEC_OBJECT_NEEDS_GTT	(1<<1)
>  #define EXEC_OBJECT_WRITE	(1<<2)
> -#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_WRITE<<1)
> +#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
> +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_SUPPORTS_48B_ADDRESS<<1)
>  	__u64 flags;
>  
>  	__u64 rsvd1;
> -- 
> 2.6.0
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx