01:09
afaerber has quit [Ping timeout: 245 seconds]
01:15
afaerber has joined #etnaviv
07:25
austriancoder has joined #etnaviv
07:59
lynxeye has joined #etnaviv
08:02
pcercuei has joined #etnaviv
08:24
austriancoder has quit [Ping timeout: 245 seconds]
08:24
smurray has quit [Read error: Connection reset by peer]
08:29
austriancoder has joined #etnaviv
08:30
smurray has joined #etnaviv
08:49
berton has quit [Remote host closed the connection]
09:26
JohnnyonFlame has joined #etnaviv
10:52
shoragan has quit [Excess Flood]
10:52
shoragan has joined #etnaviv
14:12
Chewi has quit [Ping timeout: 252 seconds]
14:35
Chewi has joined #etnaviv
16:24
lynxeye has quit [Quit: lynxeye]
18:24
<
FUZxxl >
are there plans to support this driver on FreeBSD?
18:45
flto has quit [Quit: Leaving]
18:48
<
austriancoder >
FUZxxl: not from my side - sorry
18:51
<
FUZxxl >
how unfortunate
18:55
<
marex >
austriancoder: oh hey
18:55
<
marex >
austriancoder: is there some documentation how to read the mmuv2 tables somewhere ?
18:56
<
marex >
austriancoder: I mean, I have the mmu.bin dump in front of me
18:56
<
marex >
the first 4k I guess is the MTLB
19:03
JohnnyonF has joined #etnaviv
19:06
JohnnyonFlame has quit [Ping timeout: 268 seconds]
19:07
JohnnyonF is now known as JohnnyonFlame
19:15
<
austriancoder >
marex: the kernel driver should be a good starting point
19:16
<
marex >
austriancoder: the code is written so well, it is obvious and self-documenting ? :)
19:16
<
marex >
austriancoder: ok, so let me check this obvious-ness with you
19:17
<
marex >
austriancoder: so I got the devcoredump ... I run
19:17
<
marex >
./dump/viv-unpack ~/etnaviv/new/devcoredump-20210405113612.bin | less
19:17
<
marex >
00000660 = 00000815 Cmd: [stall DMA: idle Fetch: valid] Req idle Cal idle
19:17
<
marex >
00000668 = 48000000 FE fetched word 0
19:17
<
marex >
0000066c = 00000701 FE fetched word 1
19:17
<
marex >
00000664 = 00001138 Command DMA address
19:17
<
marex >
* 2 ring 00001000 00001000 4096
19:17
<
marex >
that asterisk tells me, that the problem is in ring
19:18
<
marex >
I run ... ./tools/dump_separate_cmdbuf.py -b ~/etnaviv/new/dump/ring.bin | less
19:18
<
austriancoder >
aha
19:18
<
marex >
and that tells me ... what ? I somehow need to get from that ... to the MMU fault address
19:18
<
marex >
that should be fd945000 I suppose ...
19:19
<
marex >
except there I have some .... gap ....
19:19
<
marex >
that I need filled
19:20
<
marex >
but from there, I dump the mmu.bin with hexdump -vC mmu.bin and assuming the fault address is 0xfd945000 , I get MTLB entry 0xff8 , so ...
19:20
<
marex >
00000ff0 01 80 85 fb 01 40 85 fb 01 50 85 fb 01 60 85 fb |.....@...P...`..|
19:21
<
marex >
this ... ^^^^^^^^^^^
19:22
<
marex >
00000000 01 30 85 fb 02 00 00 00 02 00 00 00 02 00 00 00 |.0..............|
19:22
<
marex >
00000010 02 00 00 00 02 00 00 00 02 00 00 00 02 00 00 00 |................|
19:22
<
marex >
00000fe0 01 30 86 fb 01 20 86 fb 01 f0 85 fb 01 70 85 fb |.0... .......p..|
19:22
<
marex >
00000fd0 01 e0 ac fb 01 60 87 fb 01 40 86 fb 01 50 86 fb |.....`...@...P..|
19:22
<
marex >
00000ff0 01 80 85 fb 01 40 85 fb 01 50 85 fb 01 60 85 fb |.....@...P...`..|
19:22
<
marex >
this ... so I have 13 entries populated in MTLB in total, the mmu.bin is 57344 which is 1+13 * 4096, OK
19:23
<
austriancoder >
give me 15 minutes and will be in front of a device with a keyboard
19:23
<
marex >
so the MTLB entry I have is #12 (the one before last) ...
19:24
<
marex >
and for 0xfd945000 the STLB entry offset should be 0x514, so ... this ?
19:24
<
marex >
0000c510 05 a0 26 fb 05 b0 26 fb 05 c0 26 fb 05 d0 26 fb |..&...&...&...&.|
19:24
<
marex >
except the content makes little sense
19:24
<
marex >
my brain melts :)
19:58
<
marex >
austriancoder: what I dont understand is how we got from the ring dump to the MMU fault address and what are the MTLB entry values ; I understand the bottom 3 bits, not the rest
19:58
<
marex >
I guess that is PA of the TLB tables
19:59
<
marex >
*MMU tables
20:23
<
marex >
austriancoder: but that would mean that the MMU table entry is valid, and the GPU faults on valid populated MMU entry
20:49
mth has quit [Quit: Konversation terminated!]
21:17
mth has joined #etnaviv
21:55
pcercuei has quit [Quit: dodo]
21:57
chewitt has quit [Quit: Zzz..]