#asahi-gpu · 2022-03-03 14:00
phirecurrently extending my uat implementation to allocate#asahi-gpu · 2022-03-03 13:56
phirewell, I kind of just spent two weeks doing nothing but compulsivly refreshing current events#asahi-gpu · 2022-03-03 10:15
phiremaybe I should get back to gpu hacking#asahi-gpu · 2022-02-22 02:09
phirebut it might have some implications, that if it needs to fall back to emulation of a depthbuffer feature via framebuffer fetch, it needs to create a fake depth buffer color attachment#asahi-gpu · 2022-02-22 02:02
phireyeah, going back and re-reading, what they are actually saying is that GL_EXT_shader_framebuffer_fetch can't access the depth buffer#asahi-gpu · 2022-02-22 00:15
phireand making your fragment shader write the depth into it#asahi-gpu · 2022-02-22 00:14
phirethey simply recomended allocating a color attachment to hold the depth#asahi-gpu · 2022-02-22 00:14
phirealyssa, based on the optimising for metal video I watched, it appers there is no access to the hardware depth buffer#asahi-gpu · 2022-02-15 21:44
phireno major changes in structures or pointers#asahi-gpu · 2022-02-15 21:43
phiremarcan: looks like my code is all working as expected on 12.1#asahi-gpu · 2022-02-15 06:21
phireprobally much the same#asahi-gpu · 2022-02-15 06:21
phireand here is my output for m1 max 32G running 12.2 https://gist.github.com/phire/641764774ac9c5592e391c6cb01bb163#asahi-gpu · 2022-02-15 05:06
phiremax, with 64gb ram#asahi-gpu · 2022-02-15 05:06
phirewill do that after the installer finishes downloading#asahi-gpu · 2022-02-15 05:06
phiresure#asahi-gpu · 2022-02-15 05:00
phireyeah, saw it. Just need to take time to do a reinstall#asahi-gpu · 2022-02-15 04:59
phireI didn't think I'd get this deep into complex structures#asahi-gpu · 2022-02-15 04:59
phireI couldn't work out how to install an older version, so I decided to just go with 12.2 for now#asahi-gpu · 2022-02-15 04:59
phiremarcan: sorry, it's 12.2#asahi-gpu · 2022-02-15 00:57
phiremust be, but I don't see anything looking anywhere like a pointer in that region.#asahi-gpu · 2022-02-14 14:59
phireI zeroed out the region I had labled as "heap", and I got an "Instruction Abort" crashlog#asahi-gpu · 2022-02-14 14:55
phirethis initdata is a mess#asahi-gpu · 2022-02-14 14:55
phirewell, I just found what might be the gptbat pointer being passed in with the initdata#asahi-gpu · 2022-02-14 13:44
phireawkward#asahi-gpu · 2022-02-14 12:21
phirethough, that might not enough to satisfy the people conserned about backdoors. It would be a racecondition to replace the pagetables before too much of the agx-asc firmware runs#asahi-gpu · 2022-02-14 12:16
phireDoes that mean since we have control over the pagetables, we could hijack all of the agx-asc firmware except for the GFX level?#asahi-gpu · 2022-02-14 12:13
phiredidn't we have to disable CTRR to boot m1n1, or am I thinking of something else?#asahi-gpu · 2022-02-14 12:12
phireoh, that region is write protected?#asahi-gpu · 2022-02-14 12:11
phireas an alternative to auditing#asahi-gpu · 2022-02-14 12:11
phireWhat I'm wondering is could we take the bulk of apple's gfx-asc firmware, but replace the GFX level code with our own code?#asahi-gpu · 2022-02-14 12:08
phireif GXF is so small, could we rewrite it, and then graft the rest of apple's firmware onto it?#asahi-gpu · 2022-02-14 12:02
phiresometimes the 3rd field, for the compute work submission#asahi-gpu · 2022-02-14 12:01
phireFrom what I can see, context switching is controlled by second field in work submission commands. #asahi-gpu · 2022-02-14 11:38
phireI guess if the ARM core never touches the lower address range, it doesn't need to care about the gpu contexts and handle updates to gpu-region-base#asahi-gpu · 2022-02-14 11:36
phireso it just copies the two entires from gpu-region-base into into TTBR0 and TTBR1?#asahi-gpu · 2022-02-14 11:28
phireIt gets pointed at gfx-shared-region-base, and not gpu-region-base?#asahi-gpu · 2022-02-14 11:25
phireit doesn't seem to be far off, from what I can tell. But I don't know the ARM MMU very well#asahi-gpu · 2022-02-14 10:46
phireit just seems to be sign extention of bit 39#asahi-gpu · 2022-02-14 10:45
phireit gets truncated to 40 bits#asahi-gpu · 2022-02-14 10:45
phireyeah, rtkit-private-vm-region-base is 0xf80_00000000 to 0xf8f_ffffffff#asahi-gpu · 2022-02-14 10:45
phireEverything I've seen points to a unified address space#asahi-gpu · 2022-02-14 10:43
phirewell, same pagetables#asahi-gpu · 2022-02-14 10:43
phireponting at the same data?#asahi-gpu · 2022-02-14 10:42
phireI think it might be a modified ARM MMU#asahi-gpu · 2022-02-14 10:41
phirebut they got combined#asahi-gpu · 2022-02-14 10:41
phireyes. UAT seems to mean Unified Address Translater, So I'm guessing there used to be a seperate GART and DART#asahi-gpu · 2022-02-14 10:40
phireyes#asahi-gpu · 2022-02-14 10:38
phireI understand close to enough to launch a compute kernel#asahi-gpu · 2022-02-14 10:37
phireat this point I'm going to have to start on a m1n1 agx driver#asahi-gpu · 2022-02-14 10:35
phireeach L0 is 16 bytes, so they sit next to eachother at gpu-region-base