#asahi-dev · 2026-07-28 08:20
sofusyes! i think i got all 9166 bytes nailed down! https://pastebin.com/30rL1fAV#asahi-dev · 2026-07-28 07:23
svenpity, aprr_jit=0 disables the userspace JIT stuff but safari then somehow does millions of genter/exit calls so that it doesn't start anyway :(#asahi-dev · 2026-07-27 22:05
jannauno, seems to be enabled by default#asahi-dev · 2026-07-27 22:04
jannauI think marcan or lina disabled it#asahi-dev · 2026-07-27 22:03
svenisn’t it enabled by default?#asahi-dev · 2026-07-27 22:01
jannauiirc the hv doesn't hide the time it is stealing by default as that caused panics due to "insane" (from macOS' pov) power usage as well#asahi-dev · 2026-07-27 21:59
JamesCalligeros[m]no more battery life complaints#asahi-dev · 2026-07-27 21:59
JamesCalligeros[m]new power management mechanism for linux: just panic and bail if the thing uses too much power#asahi-dev · 2026-07-27 21:58
chaos_princessyes, i am constantly using clpc=0 to get anything done on 13.5#asahi-dev · 2026-07-27 21:57
JamesCalligeros[m]chaos_princess did they make those panic xnu in 13.5? i remember seeing them in the serial console and not causing a panic, but this might have been 12.x#asahi-dev · 2026-07-27 21:47
svenxnu under the cursed hv complains about heavy cpu usage from random processes here because I can’t account for the time I steal in the hv but at least it doesn’t kills anything or panic #asahi-dev · 2026-07-27 21:45
chaos_princessit is involved in power management, and the panics were all about things consuming an insane from the macos perspective amount of energy#asahi-dev · 2026-07-27 21:43
svenouch, does it not like us stealing too much time?#asahi-dev · 2026-07-27 21:33
chaos_princessunfortunately not having clpc=0 is really bad with 13.5, as any heavy tracers result in xnu panicking#asahi-dev · 2026-07-27 21:33
svenyeah. i'm glad he noticed because i probably would've spend a long time auditing my code to find that#asahi-dev · 2026-07-27 21:32
chaos_princessoh#asahi-dev · 2026-07-27 21:32
sventhat#asahi-dev · 2026-07-27 21:32
sven<jannau> you could try without "clpc=0" in boot-args if you have it. I suspect that it prevents the use of performance cores#asahi-dev · 2026-07-27 21:29
chaos_princesswhat was preventing using pcores before?#asahi-dev · 2026-07-27 21:23
svenhttps://f.svpe.de/9273c4c464e6f1a9d9ec631c37c9b3f4174eab1b85c9598992f0ffb5e2806c69_fast.jpeg still a bit of overhead but much better :-)#asahi-dev · 2026-07-27 21:19
JamesCalligeros[m]Lets gooooo#asahi-dev · 2026-07-27 21:11
svenlol, and by not doing dumb shit like taking the bhl for everything this is actually usable now and doesn't lag anymore#asahi-dev · 2026-07-27 20:07
sven 14 files changed, 1412 insertions(+), 42 deletions(-) surprisingly small diff for the core of this cursed thing :D#asahi-dev · 2026-07-27 19:14
sventime to clean this up i guess#asahi-dev · 2026-07-27 19:11
svenand anything like safari that uses userspace jit will just crash#asahi-dev · 2026-07-27 19:10
svenalright, this should probably be fast enough for hw tracing except for maybe gpu.#asahi-dev · 2026-07-27 18:34
sveni actually removed the clpc node from the ADT because i ran into a panic when trying single cpu boot#asahi-dev · 2026-07-27 18:33
svenjannau: yup, that seems to have fixed it. thanks!#asahi-dev · 2026-07-27 18:33
nickchanthe default 600 mhz is probably too slow#asahi-dev · 2026-07-27 18:33
nickchanand if someone are to check the fast uart on m1, they will need to increase cpu speed first#asahi-dev · 2026-07-27 18:31
jannauyou could try without "clpc=0" in boot-args if you have it. I suspect that it prevents the use of performance cores#asahi-dev · 2026-07-27 18:25
svenyou can see just how inefficient this entire thing is though. most of the red part is probably the HV doing its thing with pagetables#asahi-dev · 2026-07-27 18:22
svenhttps://f.svpe.de/ed300e454de66186311e0059c43330f49532f4020a4c0e1c542f4c9dcace06b9_smp.jpeg no idea why it doesn't want to use the performance cores :(#asahi-dev · 2026-07-27 18:18
nickchanit does work on a11 but i do not have the physical uart on m1 to tell if it could work there#asahi-dev · 2026-07-27 18:18
nickchanand a10 don't want to work for whatever reason that doesn't seem to be cpu speed related#asahi-dev · 2026-07-27 18:17
nickchanon some devices i could make the proxy uart go to 3 mbps but not on every device i have some devices are just too slow to handle that#asahi-dev · 2026-07-27 18:17
nickchanhttps://paste.debian.net/hidden/6e952dc9#asahi-dev · 2026-07-27 18:16
nickchanoversample rate = 0x10 - bit [19:16] of UBDRIV#asahi-dev · 2026-07-27 18:16
nickchanbit [19:16] of UBDRIV seems to control the oversampling rate#asahi-dev · 2026-07-27 18:14
nickchanso in my inability to make usb work properly on the pre-M1 devices i did found a way to make uart go faster than 1.5 mbps#asahi-dev · 2026-07-27 18:13
nickchanthose versions are when sptm is added to the device#asahi-dev · 2026-07-27 17:45
LarstiQnickchan: you mean for what os versions to cut off support?#asahi-dev · 2026-07-27 17:44
LarstiQsven: heh :)#asahi-dev · 2026-07-27 16:59
svenstill crashing with smp, but in a different way now :D#asahi-dev · 2026-07-27 15:15
nickchanthe only sensible order is here is iPhone > iPad > Macs, and New > Old#asahi-dev · 2026-07-27 15:12
nickchanmy table on things that could have sptm, but do not have them in every version: https://gist.github.com/asdfugil/101ae32734938cf2c186ff330fba1e97#asahi-dev · 2026-07-27 14:56
svenoh, lol, the corruption is because i've eaten all of m1n1's heap and kept writing into the guest's memory space :D#asahi-dev · 2026-07-27 12:28
aites[m]but I agree it would be more modular if we could separate them#asahi-dev · 2026-07-27 12:26
aites[m]:((