#
#asahi-gpu · 2022-02-08 06:46
phireit has the PMGR and MCC devices mapped in
#asahi-gpu · 2022-02-08 06:45
phireah, there is an offset
#asahi-gpu · 2022-02-08 06:39
phireand the ADT doesnt' seem to know about any of these ranges
#asahi-gpu · 2022-02-08 06:36
phireand a few extra
#asahi-gpu · 2022-02-08 06:36
phirethen kernel adds a bunch more IO ranges, including the sgx ranges
#asahi-gpu · 2022-02-08 06:35
phireok, at boot, gfx-asc only has it's own IO ranges mapped into it's pagetable
#asahi-gpu · 2022-02-08 02:40
marcanack, no rush
#asahi-gpu · 2022-02-08 02:40
phireI don't have enought time to infodump right now
#asahi-gpu · 2022-02-08 02:39
marcansure!
#asahi-gpu · 2022-02-08 02:39
phirehow about tomorrow if I haven't made any progress?
#asahi-gpu · 2022-02-08 02:39
marcanif so, would be nice if you can briefly infodump what you have (text file or whatever is fine)
#asahi-gpu · 2022-02-08 02:38
marcanI'm thinking of streaming pretty soon today too, so let me know ;)
#asahi-gpu · 2022-02-08 02:38
phireI'm not 100% stuck yet, but maybe
#asahi-gpu · 2022-02-08 02:37
marcanI was planning on doing PMU stuff but... :p
#asahi-gpu · 2022-02-08 02:37
marcanphire: should I poke a stick at it today, see if I find anything?
#asahi-gpu · 2022-02-08 02:36
marcanhmm
#asahi-gpu · 2022-02-08 02:27
phire(that's probally not a memory region)
#asahi-gpu · 2022-02-08 02:25
phire(except for ttbat-phys-addr-base, which I don't understand)
#asahi-gpu · 2022-02-08 02:25
phirebut I have traced the entire IO range around the sgx registers, and every single memory region mentioned in the sgx node
#asahi-gpu · 2022-02-08 02:24
phireI haven't tired tracing *everything* yet. I suspect would need a good handle on when a work submission might be happen before that would be viable
#asahi-gpu · 2022-02-08 01:48
marcanI'd rather avoid looking at the kext at this stage
#asahi-gpu · 2022-02-08 01:48
marcanphire: have you tried just tracing everything, possibly including parts of that memory range? (may or may not work)
#asahi-gpu · 2022-02-07 23:21
phireI'm supicious the comunication channel is simply not listed in ADT
#asahi-gpu · 2022-02-07 23:20
phiremarcan: how would you feel if I had to RE the AGXG13X kext? Because I'm really lost and not finding the communication channel that gpu work is submitted over
#asahi-gpu · 2022-02-07 23:13
alyssano way that could go wrong ;-p
#asahi-gpu · 2022-02-07 23:12
phireyes, I raised my eyebrows when I realised that. The pagetages controlling the 0xffffff8000000000 range get mapped into UAT too
#asahi-gpu · 2022-02-07 23:10
alyssano way that could go wrong ;-p
#asahi-gpu · 2022-02-07 23:10
alyssafun
#asahi-gpu · 2022-02-07 23:09
phiremarcan: yeah, the UAT iommu is "unified" and covers the ASC stuff (at 0xffffff8000000000) and the gpu allocations from userspace (useally at around 0x1500000000)
#asahi-gpu · 2022-02-07 21:38
saddsaasdhttps://worldhacker.org/index.php/irc-server/ COME TO Us , Let's Learn 0day together ... . everyone welcome , after audit ... . United Nations Candidate open now ...
#asahi-gpu · 2022-02-07 19:18
sven*that
#asahi-gpu · 2022-02-07 19:18
svensounds like it maps those with thus UAT iommu as well, which also makes sense I guess
#asahi-gpu · 2022-02-07 18:38
marcanbut you don't care about any of that
#asahi-gpu · 2022-02-07 18:38
marcanyes they have page tables and data sections and the code is readable too
#asahi-gpu · 2022-02-07 18:38
marcanphire: don't get confused by all the ASC side junk
#asahi-gpu · 2022-02-07 09:31
phireoh, it's the firmware from iboot
#asahi-gpu · 2022-02-07 09:07
phirequite a few of them, actually
#asahi-gpu · 2022-02-07 09:07
phireIf so, the gpu firmware has already initilized a bunch of page tables. Some of them point into phyisical memory
#asahi-gpu · 2022-02-07 09:04
phirewith only two entries in L0
#asahi-gpu · 2022-02-07 09:04
phirewait... this might actually be single four level page table
#asahi-gpu · 2022-02-07 08:08
svenjust be glad you didn't decide to look into DCP instead. that thing's full of magic structs from what i can tell
#asahi-gpu · 2022-02-07 07:43
phireslightly annoying for writing a driver, we will have to understand and recreate this initilzation struct to make the firmware happy
#asahi-gpu · 2022-02-07 07:16
svenyes
#asahi-gpu · 2022-02-07 07:15
phirewell, something is responding to ASC messages on boot, I assume that's the firmware
#asahi-gpu · 2022-02-07 07:15
svenerm, let me check. but iirc it was just a list of u64s (paddr, size, iova) or something similar
#asahi-gpu · 2022-02-07 07:15
svenusually the CPU needs to map in the firmware for most of these co-processors. it's usually just already done by iBoot fwiw
#asahi-gpu · 2022-02-07 07:15
phirehow do I decode segment ranges?
#asahi-gpu · 2022-02-07 07:14
phireI think it's actually CPU controlled
#asahi-gpu · 2022-02-07 07:14
phireThis is an address that has been mapped in via UAT
#asahi-gpu · 2022-02-07 07:13
sventhere's a segment-ranges property in the ADT that usually contains the mapping for the firmware fwiw

plus ›