Code is expecing to observe the same number of buffers returned from
dma_map_sg() function compared to sg_alloc_table_from_pages(). This
doesn't hold true universally especially for systems with IOMMU.
The hardware actually needs the dma_address on a page by page basis.
Joining multiple consecutive pages into one entry is just additional
overhead which we don't need.
Signed-off-by: Sinan Kaya <okaya@xxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index af1b879..91abe1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1948,6 +1948,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
/* init the mode config */
drm_mode_config_init(adev->ddev);
+ /* limit scatter-gather buffer size to PAGE_SIZE */
+ dma_set_max_seg_size(adev->dev, PAGE_SIZE);
+
r = amdgpu_device_ip_init(adev);
if (r) {
/* failed in exclusive mode due to timeout */
--
2.7.4
_______________________________________________
dri-devel mailing list
dri-devel@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/dri-devel
