Am 14.05.19 um 12:24 schrieb Tiecheng Zhou:
it requires to initialize HDP_NONSURFACE_BASE, so as to avoid
using the value left by a previous VM under sriov scenario.
Signed-off-by: Emily Deng <Emily.Deng@xxxxxxx>
Signed-off-by: Tiecheng Zhou <Tiecheng.Zhou@xxxxxxx>
Would it hurt us to also do this on bare metal?
Apart from that looks good to me,
Christian.
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index be729e7..e96684e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1181,6 +1181,11 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
tmp = RREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL);
WREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL, tmp);
+ if (amdgpu_sriov_vf(adev)) {
+ WREG32_SOC15(HDP, 0, mmHDP_NONSURFACE_BASE, (adev->gmc.vram_start >> 8));
+ WREG32_SOC15(HDP, 0, mmHDP_NONSURFACE_BASE_HI, (adev->gmc.vram_start >> 40));
+ }
+
/* After HDP is initialized, flush HDP.*/
adev->nbio_funcs->hdp_flush(adev, NULL);
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx