From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 109127] E9260 not working with recent software/firmware Date: Fri, 21 Dec 2018 09:37:52 +0000 Message-ID: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1562350722==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [IPv6:2610:10:20:722:a800:ff:fe98:4b55]) by gabe.freedesktop.org (Postfix) with ESMTP id EBE366F587 for ; Fri, 21 Dec 2018 09:37:52 +0000 (UTC) List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============1562350722== Content-Type: multipart/alternative; boundary="15453850720.bE1f3.30603" Content-Transfer-Encoding: 7bit --15453850720.bE1f3.30603 Date: Fri, 21 Dec 2018 09:37:52 +0000 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated https://bugs.freedesktop.org/show_bug.cgi?id=3D109127 Bug ID: 109127 Summary: E9260 not working with recent software/firmware Product: DRI Version: unspecified Hardware: x86-64 (AMD64) OS: Linux (All) Status: NEW Severity: blocker Priority: medium Component: DRM/AMDgpu Assignee: dri-devel@lists.freedesktop.org Reporter: john.alexander@datapath.co.uk 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. --=20 You are receiving this mail because: You are the assignee for the bug.= --15453850720.bE1f3.30603 Date: Fri, 21 Dec 2018 09:37:52 +0000 MIME-Version: 1.0 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated
Bug ID 109127
Summary E9260 not working with recent software/firmware
Product DRI
Version unspecified
Hardware x86-64 (AMD64)
OS Linux (All)
Status NEW
Severity blocker
Priority medium
Component DRM/AMDgpu
Assignee dri-devel@lists.freedesktop.org
Reporter john.alexander@datapath.co.uk 

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.

You are receiving this mail because:
  • You are the assignee for the bug.
= --15453850720.bE1f3.30603-- --===============1562350722== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============1562350722==--