linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v5] drm/virtio: use virtio_max_dma_size
@ 2019-08-21 11:12 Gerd Hoffmann
  2019-08-22 11:33 ` Laszlo Ersek
  0 siblings, 1 reply; 2+ messages in thread
From: Gerd Hoffmann @ 2019-08-21 11:12 UTC (permalink / raw)
  To: dri-devel
  Cc: László Érsek, Gerd Hoffmann, David Airlie,
	Daniel Vetter, open list:VIRTIO GPU DRIVER, open list

We must make sure our scatterlist segments are not too big, otherwise
we might see swiotlb failures (happens with sev, also reproducable with
swiotlb=force).

Suggested-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
 drivers/gpu/drm/virtio/virtgpu_object.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index b2da31310d24..09b526518f5a 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -204,6 +204,7 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev,
 		.interruptible = false,
 		.no_wait_gpu = false
 	};
+	size_t max_segment;
 
 	/* wtf swapping */
 	if (bo->pages)
@@ -215,8 +216,13 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev,
 	if (!bo->pages)
 		goto out;
 
-	ret = sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
-					nr_pages << PAGE_SHIFT, GFP_KERNEL);
+	max_segment = virtio_max_dma_size(qdev->vdev);
+	max_segment &= PAGE_MASK;
+	if (max_segment > SCATTERLIST_MAX_SEGMENT)
+		max_segment = SCATTERLIST_MAX_SEGMENT;
+	ret = __sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
+					  nr_pages << PAGE_SHIFT,
+					  max_segment, GFP_KERNEL);
 	if (ret)
 		goto out;
 	return 0;
-- 
2.18.1


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH v5] drm/virtio: use virtio_max_dma_size
  2019-08-21 11:12 [PATCH v5] drm/virtio: use virtio_max_dma_size Gerd Hoffmann
@ 2019-08-22 11:33 ` Laszlo Ersek
  0 siblings, 0 replies; 2+ messages in thread
From: Laszlo Ersek @ 2019-08-22 11:33 UTC (permalink / raw)
  To: Gerd Hoffmann, dri-devel
  Cc: David Airlie, Daniel Vetter, open list:VIRTIO GPU DRIVER, open list

On 08/21/19 13:12, Gerd Hoffmann wrote:
> We must make sure our scatterlist segments are not too big, otherwise
> we might see swiotlb failures (happens with sev, also reproducable with
> swiotlb=force).
> 
> Suggested-by: Laszlo Ersek <lersek@redhat.com>
> Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
> ---
>  drivers/gpu/drm/virtio/virtgpu_object.c | 10 ++++++++--
>  1 file changed, 8 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
> index b2da31310d24..09b526518f5a 100644
> --- a/drivers/gpu/drm/virtio/virtgpu_object.c
> +++ b/drivers/gpu/drm/virtio/virtgpu_object.c
> @@ -204,6 +204,7 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev,
>  		.interruptible = false,
>  		.no_wait_gpu = false
>  	};
> +	size_t max_segment;
>  
>  	/* wtf swapping */
>  	if (bo->pages)
> @@ -215,8 +216,13 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev,
>  	if (!bo->pages)
>  		goto out;
>  
> -	ret = sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
> -					nr_pages << PAGE_SHIFT, GFP_KERNEL);
> +	max_segment = virtio_max_dma_size(qdev->vdev);
> +	max_segment &= PAGE_MASK;
> +	if (max_segment > SCATTERLIST_MAX_SEGMENT)
> +		max_segment = SCATTERLIST_MAX_SEGMENT;
> +	ret = __sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
> +					  nr_pages << PAGE_SHIFT,
> +					  max_segment, GFP_KERNEL);
>  	if (ret)
>  		goto out;
>  	return 0;
> 

Reviewed-by: Laszlo Ersek <lersek@redhat.com>

Thanks!
Laszlo

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2019-08-22 11:33 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-08-21 11:12 [PATCH v5] drm/virtio: use virtio_max_dma_size Gerd Hoffmann
2019-08-22 11:33 ` Laszlo Ersek

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).