Comme=
nt # 94
on bug 11067=
4
from Tom =
B
Reverting d1a3e239a6016f2bb42a91696056e223982e8538 didn't fix =
it for me. But
that commit may give some insight because it is related to uclk which is the
first error we get.
I also tried globally increasing usec_timeout as it's used in a few places
(patch below). This makes the PC take about a minute to boot up, so clearly=
the
GPU is in an invalid state before these timeouts are hit and then each
subsequent call to smum_send_msg_to_smc_with_parameter causes a delay becau=
se
each call times out. Whatever happens, puts the card into a state that it c=
an't
recover from.
The next step is to try to find where vega20_set_uclk_to_highest_dpm_level =
is
called from and see what happens just before the call to this function.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f4ac632a87b2..9b878c74b17e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2418,7 +2418,7 @@ int amdgpu_device_init(struct amdgpu_=
device *adev,
adev->pdev =3D pdev;
adev->flags =3D flags;
adev->asic_type =3D flags & AMD_ASIC_MASK;
- adev->usec_timeout =3D AMDGPU_MAX_USEC_TIMEOUT;
+ adev->usec_timeout =3D AMDGPU_MAX_USEC_TIMEOUT*10;
if (amdgpu_emu_mode =3D=3D 1)
adev->usec_timeout *=3D 2;
adev->gmc.gart_size =3D 512 * 1024 * 1024;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index a7e8340baf90..a6b2bc4277ef 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -84,7 +84,7 @@ int hwmgr_early_init(struct pp_hwmgr *hwm=
gr)
if (!hwmgr)
return -EINVAL;
- hwmgr->usec_timeout =3D AMD_MAX_USEC_TIMEOUT;
+ hwmgr->usec_timeout =3D AMD_MAX_USEC_TIMEOUT*10;
hwmgr->pp_table_version =3D PP_TABLE_V1;
hwmgr->dpm_level =3D AMD_DPM_FORCED_LEVEL_AUTO;
hwmgr->request_dpm_level =3D AMD_DPM_FORCED_LEVEL_AUTO;