Remove __GFP_HIGHMEM when requesting a page from DMA32 zone,
and since all vivante GPUs in the system will share the same
DMA constraints, move the check of whether to get a page from
DMA32 to etnaviv_bind().

Fixes: b72af445cd38 ("drm/etnaviv: request pages from DMA32 zone when needed")
Suggested-by: Sui Jingfeng <sui.jingfeng@linux.dev>
Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com>
---
v1:
  https://patchwork.kernel.org/project/dri-devel/patch/20240806104733.2018783-1-xiaolei.wang@windriver.com/

v2:
  Modify the issue of not retaining GFP_USER in v1 and update the commit log.

v3:
  Use "priv->shm_gfp_mask = GFP_USER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;"
instead of
  "priv->shm_gfp_mask = GFP_HIGHUSER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;"

v4:
  drop the HIGHMEM bit only if dma addressing is limited.

 drivers/gpu/drm/etnaviv/etnaviv_drv.c | 10 ++++++++++
 drivers/gpu/drm/etnaviv/etnaviv_gpu.c |  8 --------
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 6500f3999c5f..19ec67a5a918 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -538,6 +538,16 @@ static int etnaviv_bind(struct device *dev)
 	priv->num_gpus = 0;
 	priv->shm_gfp_mask = GFP_HIGHUSER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
 
+	/*
+	 * If the GPU is part of a system with DMA addressing limitations,
+	 * request pages for our SHM backend buffers from the DMA32 zone to
+	 * hopefully avoid performance killing SWIOTLB bounce buffering.
+	 */
+	if (dma_addressing_limited(dev)) {
+		priv->shm_gfp_mask |= GFP_DMA32;
+		priv->shm_gfp_mask &= ~__GFP_HIGHMEM;
+	}
+
 	priv->cmdbuf_suballoc = etnaviv_cmdbuf_suballoc_new(drm->dev);
 	if (IS_ERR(priv->cmdbuf_suballoc)) {
 		dev_err(drm->dev, "Failed to create cmdbuf suballocator\n");
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 7c7f97793ddd..5e753dd42f72 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -839,14 +839,6 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	if (ret)
 		goto fail;
 
-	/*
-	 * If the GPU is part of a system with DMA addressing limitations,
-	 * request pages for our SHM backend buffers from the DMA32 zone to
-	 * hopefully avoid performance killing SWIOTLB bounce buffering.
-	 */
-	if (dma_addressing_limited(gpu->dev))
-		priv->shm_gfp_mask |= GFP_DMA32;
-
 	/* Create buffer: */
 	ret = etnaviv_cmdbuf_init(priv->cmdbuf_suballoc, &gpu->buffer,
 				  PAGE_SIZE);
-- 
2.25.1

Am Mittwoch, dem 02.10.2024 um 07:34 +0800 schrieb Xiaolei Wang:
> Remove __GFP_HIGHMEM when requesting a page from DMA32 zone,
> and since all vivante GPUs in the system will share the same
> DMA constraints, move the check of whether to get a page from
> DMA32 to etnaviv_bind().
> 
> Fixes: b72af445cd38 ("drm/etnaviv: request pages from DMA32 zone when needed")
> Suggested-by: Sui Jingfeng <sui.jingfeng@linux.dev>
> Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
> Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com>

Thanks, applied to etnaviv/next.

> ---
> v1:
>   https://patchwork.kernel.org/project/dri-devel/patch/20240806104733.2018783-1-xiaolei.wang@windriver.com/
> 
> v2:
>   Modify the issue of not retaining GFP_USER in v1 and update the commit log.
> 
> v3:
>   Use "priv->shm_gfp_mask = GFP_USER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;"
> instead of
>   "priv->shm_gfp_mask = GFP_HIGHUSER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;"
> 
> v4:
>   drop the HIGHMEM bit only if dma addressing is limited.
> 
>  drivers/gpu/drm/etnaviv/etnaviv_drv.c | 10 ++++++++++
>  drivers/gpu/drm/etnaviv/etnaviv_gpu.c |  8 --------
>  2 files changed, 10 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> index 6500f3999c5f..19ec67a5a918 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> @@ -538,6 +538,16 @@ static int etnaviv_bind(struct device *dev)
>  	priv->num_gpus = 0;
>  	priv->shm_gfp_mask = GFP_HIGHUSER | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
>  
> +	/*
> +	 * If the GPU is part of a system with DMA addressing limitations,
> +	 * request pages for our SHM backend buffers from the DMA32 zone to
> +	 * hopefully avoid performance killing SWIOTLB bounce buffering.
> +	 */
> +	if (dma_addressing_limited(dev)) {
> +		priv->shm_gfp_mask |= GFP_DMA32;
> +		priv->shm_gfp_mask &= ~__GFP_HIGHMEM;
> +	}
> +
>  	priv->cmdbuf_suballoc = etnaviv_cmdbuf_suballoc_new(drm->dev);
>  	if (IS_ERR(priv->cmdbuf_suballoc)) {
>  		dev_err(drm->dev, "Failed to create cmdbuf suballocator\n");
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
> index 7c7f97793ddd..5e753dd42f72 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
> @@ -839,14 +839,6 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
>  	if (ret)
>  		goto fail;
>  
> -	/*
> -	 * If the GPU is part of a system with DMA addressing limitations,
> -	 * request pages for our SHM backend buffers from the DMA32 zone to
> -	 * hopefully avoid performance killing SWIOTLB bounce buffering.
> -	 */
> -	if (dma_addressing_limited(gpu->dev))
> -		priv->shm_gfp_mask |= GFP_DMA32;
> -
>  	/* Create buffer: */
>  	ret = etnaviv_cmdbuf_init(priv->cmdbuf_suballoc, &gpu->buffer,
>  				  PAGE_SIZE);