<div dir="ltr"><div><div>Hi,<br><br></div>Wladimir, Fabio: Thanks for pointing out this patch. I have applied the patch and compiled mesa, but it produced no relevant change regarding the MMU fault that I am getting. For me it makes sense that it isn't related to this issue because I am running no 3D applications, just logging in into the Ubuntu MATE Desktop. Since I am using xf86-video-armada It is expected that GC320 is the only unit busy, working, during this stage of the desktop initialization.<br><br></div>Russel, Lucas: The etna-gpu-tools compiled cleanly... I got this log and some .bin files with the dumps. I have no clue about the GC320 registers as I have no knowledge about the unit, however I if could get the stack of the calling process, would be great...<br>[ 56.173613] etnaviv-gpu 134000.gpu: MMU fault status 0x00000002 <br>[ 56.179955] etnaviv-gpu 134000.gpu: MMU 0 fault addr 0x0803ffc0 <br>[ 56.185905] etnaviv-gpu 134000.gpu: MMU 1 fault addr 0x00000000 <br>[ 56.191843] etnaviv-gpu 134000.gpu: MMU 2 fault addr 0x00000000 <br>[ 56.197778] etnaviv-gpu 134000.gpu: MMU 3 fault addr 0x00000000 <br>[ 59.258367] etnaviv-gpu 134000.gpu: hangcheck detected gpu lockup! <br>[ 59.265910] etnaviv-gpu 134000.gpu: completed fence: 378 <br>[ 59.271737] etnaviv-gpu 134000.gpu: active fence: 383 <br>[ 59.277930] etnaviv-gpu 134000.gpu: hangcheck recover! <br>[ 59.393270] etnaviv-gpu 134000.gpu: MMU fault status 0x00000002 <br>[ 59.399256] etnaviv-gpu 134000.gpu: MMU 0 fault addr 0x00343fc0 <br>[ 59.405207] etnaviv-gpu 134000.gpu: MMU 1 fault addr 0x00000000 <br>[ 59.411143] etnaviv-gpu 134000.gpu: MMU 2 fault addr 0x00000000 <br>[ 59.417082] etnaviv-gpu 134000.gpu: MMU 3 fault addr 0x00000000 <br>[ 61.272368] etnaviv-gpu 134000.gpu: hangcheck detected gpu lockup! <br>[ 61.278633] etnaviv-gpu 134000.gpu: completed fence: 384 <br>[ 61.284515] etnaviv-gpu 134000.gpu: active fence: 387 <br>[ 61.290110] etnaviv-gpu 134000.gpu: hangcheck recover! <br>[ 62.278720] etnaviv-gpu 134000.gpu: MMU fault status 0x00000002 <br>[ 62.284699] etnaviv-gpu 134000.gpu: MMU 0 fault addr 0x0803ffc0 <br>[ 62.290681] etnaviv-gpu 134000.gpu: MMU 1 fault addr 0x00000000 <br>[ 62.296644] etnaviv-gpu 134000.gpu: MMU 2 fault addr 0x00000000 <br>[ 62.302603] etnaviv-gpu 134000.gpu: MMU 3 fault addr 0x00000000 <br>[ 64.306760] etnaviv-gpu 134000.gpu: hangcheck detected gpu lockup! <br>[ 64.313031] etnaviv-gpu 134000.gpu: completed fence: 387 <br>[ 64.318907] etnaviv-gpu 134000.gpu: active fence: 403 <br>[ 64.325477] etnaviv-gpu 134000.gpu: hangcheck recover! <br><br>=== Register dump<br>0000000c = 000000df<br>00000000 = 00040900<br>00000004 = 7ffffff8 Idle: FE- DE- PE- SH+ PA+ SE+ RA+ TX+ VG+ IM+ FP+ TS+<br>00000008 = 00002200<br>00000014 = ffffffff<br>00000018 = 14010000<br>0000001c = e02c7eca<br>00000020 = 00000320<br>00000024 = 00005303<br>00000028 = 20140510<br>0000002c = 20353900<br>00000034 = e9399eff<br>00000038 = e9399eff<br>00000070 = 00000000<br>00000100 = 00140021<br>00000104 = 00000000<br>00000108 = 000000fa<br>0000010c = 00000000<br>00000400 = 00000000<br>00000404 = 00000000<br>00000408 = 00000000<br>0000040c = 00000000 <br>00000410 = 00000000 <br>00000414 = 3c000000 <br>00000418 = 00000000 <br>0000041c = 00000000 <br>00000420 = 00000000 <br>00000424 = 00000000 <br>00000428 = 00000000 <br>0000042c = 00030000 <br>00000480 = 000000a8 <br>0000065c = 00000001 <br>00000660 = 00000803 Cmd: [load0 DMA: idle Fetch: valid] Req idle Cal idle <br>00000664 = 00001230 Command DMA address <br>00000668 = 00000040 FE fetched word 0 <br>0000066c = 00000000 FE fetched word 1 <br>00000670 = 00000000 <br>=== Buffers <br> Num Name IOVA Size <br> 0 reg 00000000 00000128 296 <br> 1 mmu 00000000 00401000 4198400 <br> 2 ring 00000000 00001000 4096 <br>* 3 cmd 00001000 00000320 800 <br> 4 cmd 00002000 00000190 400 <br> 5 cmd 00003000 00000320 800 <br> 6 cmd 00004000 00000190 400 <br> 7 cmd 00005000 00000188 392 <br> 8 bomap 00000000 000018f0 6384 <br> 9 bo 00040000 00300000 3145728 <br> 10 bo 00340000 00001000 4096 <br> 11 bo 00341000 00002000 8192 <br> 12 bo 02e60000 00001000 4096 <br> 13 bo 030c3000 00001000 4096 <br> 14 bo 030c4000 00001000 4096 <br> 15 bo 030c5000 00018000 98304 <br>Checking MMU entries... ok <br><br><br><div class="gmail_extra"><div class="gmail_quote">On Thu, Nov 2, 2017 at 1:36 PM, Fabio Estevam <span dir="ltr"><<a href="mailto:festevam@gmail.com" target="_blank">festevam@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Hi Luís,<br>
<span class="gmail-"><br>
On Thu, Nov 2, 2017 at 9:21 AM, Wladimir J. van der Laan<br>
<<a href="mailto:laanwj@gmail.com">laanwj@gmail.com</a>> wrote:<br>
<br>
> Make sure you have<br>
><br>
> commit 8fbd82f464f26a56167f7962174b2b<wbr>69756a105a etnaviv: don't do resolve-in-place without valid TS<br>
><br>
> This was a source of MMU faults with etnaviv GC3000,<br>
<br>
</span>This commit can be found in the master mesa branch:<br>
<a href="https://cgit.freedesktop.org/mesa/mesa/commit/?id=8fbd82f464f26a56167f7962174b2b69756a105a" rel="noreferrer" target="_blank">https://cgit.freedesktop.org/<wbr>mesa/mesa/commit/?id=<wbr>8fbd82f464f26a56167f7962174b2b<wbr>69756a105a</a><br>
<br>
It is not part of mesa 17.2.4, so please apply it manually and let us<br>
know if it fixes the MMU faults.<br>
<br>
Regards,<br>
<br>
Fabio Estevam<br>
</blockquote></div><br></div></div>