Using recent AMDGPU source code and recent firmware files for =
the E9260 GPU
(Polaris11, deviceID:67E8h) the GPU fails to initialise correctly. Debuggi=
ng
shows that the RLC times out entering safe mode, further debugging shows th=
is
is because the SMU has uploaded garbage firmware.
I've had a pcie interposer/bus analyser inline with this GPU and can see th=
at
the issue is that GTT addresses are not being translated. When the SMU req=
uest
to load firmware is sent the PCIe read operations contain the GPU MC addres=
ses,
not the system page addresses as they have been programmed within the gart
table. If we shunt the firmware bo and the SMUs firmware header allocations
into VRAM rather than the GTT the firmware is correctly uploaded; the net
result is that GFX ring tests then fail with similar results; The GPU can t=
hen
be observed attempting to read from the GFX ring but the addresses used acr=
oss
the PCIe bus are the MC ring addresses, not the system page addresses.