#asahi-gpu · 2022-11-12 17:41
jannaugah, using dcp from two entry points (kms and backlight device) at the same time to swap surfaces / brightness works as well as one can imagine#asahi-gpu · 2022-11-11 22:53
jannauintegrated + discrete gpus in laptops#asahi-gpu · 2022-11-11 22:44
jannauI guess so, that is for PRIME and not kmsro#asahi-gpu · 2022-11-11 22:33
jannauis draw->is_different_gpu expected to be false?#asahi-gpu · 2022-11-11 22:25
jannauhttps://paste.debian.net/1260400/#asahi-gpu · 2022-11-11 22:23
jannauthe culprit for glxgears seems to be dri3_alloc_render_buffer() src/loader/loader_dri3_helper.c line 1526#asahi-gpu · 2022-11-11 22:11
jannauyes#asahi-gpu · 2022-11-11 22:09
jannaugbm_bo_create_with_modifiers() always sets GBM_BO_USE_SCANOUT#asahi-gpu · 2022-11-11 22:09
jannauincreasing the address space doesn't doesn't fix leaks. this was more a thought if there's enough fb address space for 9 display setups on the m1 ultra #asahi-gpu · 2022-11-11 20:15
jannaut8103 has a vm-size of 0xfc00_0000 which appears more of a suggestions since linux starts mapping at the top end of the full 32-bit space#asahi-gpu · 2022-11-11 20:13
jannauI wonder how large disp0's iova space is. no vm-size property in t600x ADT for dart-disp0, so it could be (36-bit)#asahi-gpu · 2022-11-10 21:21
jannaualyssa: turns out iova.c works if used properly. proper fix pushed. "leaked" memory is freed on terminating weston#asahi-gpu · 2022-11-09 23:23
jannaualyssa, lina: https://github.com/jannau/linux/tree/gpu/rust-wip-dcp first patch is already in asahi-wip, fixes a dart build as module, 2nd commit prevents hitting that warning in dart_map_pages() but of course doesn't fix exhausting the iova space through memory leaks#asahi-gpu · 2022-11-09 22:52
jannauI wonder if the issues with reserved low iova would go away with unmanaged iommu domains. I suspose it'll remain a problem disp0 which I'd like to keep managed though#asahi-gpu · 2022-11-09 22:38
jannauI found an ugly workaround: exclude the low reserved iova via aperture_start#asahi-gpu · 2022-11-09 22:02
jannaumaximbaz: add module_blacklist=apple_dcp to the kernel commandline#asahi-gpu · 2022-11-09 21:45
jannaulooks like iova.c can't handle that there's reserved mem at iova 0x0#asahi-gpu · 2022-11-09 21:32
jannauyou could try to block dcp to see if that gives more information#asahi-gpu · 2022-11-09 21:13
jannauwth! dma_alloc_coherent() fails#asahi-gpu · 2022-11-09 21:06
jannauI guess the display could also freeze because dcp takes over. it would be helpful if you can boot with m1n1's hypervisor and the virtual uart#asahi-gpu · 2022-11-09 20:55
jannaubut fixing it breaks dcp since it prevents now the memmap of the rtkit shmem#asahi-gpu · 2022-11-09 20:52
jannauso, yes, the leak found a bug via the WARN_ON#asahi-gpu · 2022-11-09 20:51
jannaukernel bug spotted. it reserves the physical address. oversight on my part when I added support for translated reserved regions#asahi-gpu · 2022-11-09 20:32
jannauit tries to map something in the middle of the boot framebuffer#asahi-gpu · 2022-11-09 20:16
jannaudart-disp0 stream 0 looks full, except for some small gaps#asahi-gpu · 2022-11-09 20:11
jannauso possible just a bug in the reserved memory handling on iommu side#asahi-gpu · 2022-11-09 20:10
jannauso the leak exhaust all iova space and the iommu code tries to use the boot mappings#asahi-gpu · 2022-11-09 20:06
jannaumaybe an issue with the reserved memory#asahi-gpu · 2022-11-09 20:05
jannauit is WARN_ON(ptep[i] & APPLE_DART_PTE_VALID) from the inlined dart_init_pte()#asahi-gpu · 2022-11-09 19:59
jannaureproduced#asahi-gpu · 2022-11-09 19:48
jannaufunky, it takes ~2 seconds in weston+Xwayland until the glxgears window vanishes#asahi-gpu · 2022-11-09 19:33
jannauwithout the extra commits#asahi-gpu · 2022-11-09 19:33
jannau`kodi --windowing=x11` works somewhat, video playback stops after a few seconds and it hangs at exit, I have to kill -9 it#asahi-gpu · 2022-11-09 19:30
jannaumaximbaz: asahi.debug_flags=...#asahi-gpu · 2022-11-09 18:47
jannauI see now warnings with kodi but video playback is very broken#asahi-gpu · 2022-11-09 18:23
jannaualyssa: asahi/rebased still works on t6002#asahi-gpu · 2022-11-09 18:06
jannaubuilds mesa right now to look at the dart warning#asahi-gpu · 2022-11-09 18:04
jannauhotplug handling might have changed as well#asahi-gpu · 2022-11-09 18:04
jannaualyssa: I see that with dcpext as well, the link-status bad call is still there with the comment but I had to guard it with checks to avoid NULL ptr derefs#asahi-gpu · 2022-11-08 23:24
jannaumaximbaz: does the device have 32GB RAM? is there a warning in dmesg?#asahi-gpu · 2022-11-08 20:25
jannauI guess "WARN_ON(paddr >> cfg->oas)" is very unlikely, what could cause "WARN_ON(pgsize != cfg->pgsize_bitmap)" to trigger? large pages?#asahi-gpu · 2022-11-08 20:17
jannauisn't that dcp as agx doesn't use dart?#asahi-gpu · 2022-11-07 17:32
jannaus/(sometimes)/\1,/#asahi-gpu · 2022-11-07 17:31
jannauit works on multiple devices with multiple displays (sometimes with a little bit of hand holding)#asahi-gpu · 2022-11-07 17:23
jannauyes, I think there should have been m1n1 C changes from last week#asahi-gpu · 2022-11-07 17:21
jannauI haven't tried after the latest updates since sven kept me busy with dcpext#asahi-gpu · 2022-11-07 17:18
jannauno, there are at least some updates#asahi-gpu · 2022-11-07 17:16
jannauthat looks like lina might has not updated the m1 dt after the m1 ultra changes#asahi-gpu · 2022-11-05 10:04
jannaudugsarew: change CONFIG_APPLE_DART=m to CONFIG_APPLE_DART=y in the config, should be solved the next time lina rebases on-top of asahi-wip#asahi-gpu · 2022-11-04 09:43
jannaulina: CBW. WCTA. STAC.STAS2.[ 68. 8] unk_68 = 0xed0000 - http://paste.debian.net/1259497/