Nouveau - Jul 2013 - [PATCH] drm/nouveau: do not move buffers when not needed

I have no idea what this bogus restriction on placement is, but it breaks
decoding 1080p
VDPAU at boot speed. With this patch applied I only need to bump the vdec clock
to
get real-time 1080p decoding. It prevents a lot of VRAM <-> VRAM buffer
moves.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com>
---
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c
b/drivers/gpu/drm/nouveau/nouveau_bo.c
index d506da5..86eb321 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1339,34 +1339,6 @@ nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev,
struct ttm_mem_reg *mem)
 }
 
 static int
-nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
-{
-	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_bo *nvbo = nouveau_bo(bo);
-	struct nouveau_device *device = nv_device(drm->device);
-	u32 mappable = pci_resource_len(device->pdev, 1) >> PAGE_SHIFT;
-
-	/* as long as the bo isn't in vram, and isn't tiled, we've got
-	 * nothing to do here.
-	 */
-	if (bo->mem.mem_type != TTM_PL_VRAM) {
-		if (nv_device(drm->device)->card_type < NV_50 ||
-		    !nouveau_bo_tile_layout(nvbo))
-			return 0;
-	}
-
-	/* make sure bo is in mappable vram */
-	if (bo->mem.start + bo->mem.num_pages < mappable)
-		return 0;
-
-
-	nvbo->placement.fpfn = 0;
-	nvbo->placement.lpfn = mappable;
-	nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_VRAM, 0);
-	return nouveau_bo_validate(nvbo, false, false);
-}
-
-static int
 nouveau_ttm_tt_populate(struct ttm_tt *ttm)
 {
 	struct ttm_dma_tt *ttm_dma = (void *)ttm;
@@ -1524,7 +1496,6 @@ struct ttm_bo_driver nouveau_bo_driver = {
 	.sync_obj_flush = nouveau_bo_fence_flush,
 	.sync_obj_unref = nouveau_bo_fence_unref,
 	.sync_obj_ref = nouveau_bo_fence_ref,
-	.fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
 	.io_mem_reserve = &nouveau_ttm_io_mem_reserve,
 	.io_mem_free = &nouveau_ttm_io_mem_free,
 };

On Fri, Jul 12, 2013 at 10:45 PM, Maarten Lankhorst
<maarten.lankhorst at canonical.com> wrote:
> I have no idea what this bogus restriction on placement is, but it breaks
decoding 1080p
> VDPAU at boot speed. With this patch applied I only need to bump the vdec
clock to
> get real-time 1080p decoding. It prevents a lot of VRAM <-> VRAM
buffer moves.
It's not bogus, and is required for pre-GF8 boards with VRAM > BAR size.

What configuration does the buffer that's getting moved here have
exactly?  The placement restriction isn't necessary on GF8, the rest
of the restrictions may currently be required still however.

Ben.

>
> Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com>
> ---
> diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c
b/drivers/gpu/drm/nouveau/nouveau_bo.c
> index d506da5..86eb321 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_bo.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
> @@ -1339,34 +1339,6 @@ nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev,
struct ttm_mem_reg *mem)
>  }
>
>  static int
> -nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
> -{
> -       struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
> -       struct nouveau_bo *nvbo = nouveau_bo(bo);
> -       struct nouveau_device *device = nv_device(drm->device);
> -       u32 mappable = pci_resource_len(device->pdev, 1) >>
PAGE_SHIFT;
> -
> -       /* as long as the bo isn't in vram, and isn't tiled,
we've got
> -        * nothing to do here.
> -        */
> -       if (bo->mem.mem_type != TTM_PL_VRAM) {
> -               if (nv_device(drm->device)->card_type < NV_50 ||
> -                   !nouveau_bo_tile_layout(nvbo))
> -                       return 0;
> -       }
> -
> -       /* make sure bo is in mappable vram */
> -       if (bo->mem.start + bo->mem.num_pages < mappable)
> -               return 0;
> -
> -
> -       nvbo->placement.fpfn = 0;
> -       nvbo->placement.lpfn = mappable;
> -       nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_VRAM, 0);
> -       return nouveau_bo_validate(nvbo, false, false);
> -}
> -
> -static int
>  nouveau_ttm_tt_populate(struct ttm_tt *ttm)
>  {
>         struct ttm_dma_tt *ttm_dma = (void *)ttm;
> @@ -1524,7 +1496,6 @@ struct ttm_bo_driver nouveau_bo_driver = {
>         .sync_obj_flush = nouveau_bo_fence_flush,
>         .sync_obj_unref = nouveau_bo_fence_unref,
>         .sync_obj_ref = nouveau_bo_fence_ref,
> -       .fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
>         .io_mem_reserve = &nouveau_ttm_io_mem_reserve,
>         .io_mem_free = &nouveau_ttm_io_mem_free,
>  };
>
> _______________________________________________
> dri-devel mailing list
> dri-devel at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel

Op 15-07-13 08:05, Ben Skeggs schreef:
> On Fri, Jul 12, 2013 at 10:45 PM, Maarten Lankhorst
> <maarten.lankhorst at canonical.com> wrote:
>> I have no idea what this bogus restriction on placement is, but it
breaks decoding 1080p
>> VDPAU at boot speed. With this patch applied I only need to bump the
vdec clock to
>> get real-time 1080p decoding. It prevents a lot of VRAM <-> VRAM
buffer moves.
> It's not bogus, and is required for pre-GF8 boards with VRAM > BAR
size.
>
> What configuration does the buffer that's getting moved here have
> exactly?  The placement restriction isn't necessary on GF8, the rest
> of the restrictions may currently be required still however.
>
>= vdpau on NVC0 with tiling. I upload the raw bitstream to a tiling bo. This
is ok because
the vm hides all the tiling translations, and the engines will read the raw
bitstream correctly.
8<---
This prevents buffer moves from being done on NV50+, where remapping is not
needed because
the bar has its own VM, instead of only having the first BAR1-size chunk of VRAM
accessible.
nouveau_bo_tile_layout is always 0 on < NV_50.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com>
---
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c
b/drivers/gpu/drm/nouveau/nouveau_bo.c
index d506da5..762bfcd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1346,14 +1361,13 @@ nouveau_ttm_fault_reserve_notify(struct
ttm_buffer_object *bo)
 	struct nouveau_device *device = nv_device(drm->device);
 	u32 mappable = pci_resource_len(device->pdev, 1) >> PAGE_SHIFT;
 
-	/* as long as the bo isn't in vram, and isn't tiled, we've got
-	 * nothing to do here.
+	/*
+	 * if the bo is not in vram, or remapping can be done (nv50+)
+	 * do not worry about placement, any location is valid
 	 */
-	if (bo->mem.mem_type != TTM_PL_VRAM) {
-		if (nv_device(drm->device)->card_type < NV_50 ||
-		    !nouveau_bo_tile_layout(nvbo))
-			return 0;
-	}
+	if (nv_device(drm->device)->card_type >= NV_50 ||
+	    bo->mem.mem_type != TTM_PL_VRAM)
+		return 0;
 
 	/* make sure bo is in mappable vram */
 	if (bo->mem.start + bo->mem.num_pages < mappable)