#
✕ nick:StanfordAppliedCyber[m]
#asahi-dev · 2026-07-03 09:44
StanfordAppliedCyber[m]no clue, but i don't think it's just tlbs
#asahi-dev · 2026-07-03 09:43
StanfordAppliedCyber[m]in sptm it basically keeps track of dirty pages, if below some threshold it calls 00201320 on all of them, otherwise it calls 00201401 to flush all of them
#asahi-dev · 2026-07-03 09:42
StanfordAppliedCyber[m]tl;dr 00201401 appears to be a flush of all pages, 00201320 appears to be a flush by page number, 00201300 is the same thing by address
#asahi-dev · 2026-07-03 09:41
StanfordAppliedCyber[m]re: custom cache instructions, sptm has some new instructions present only on m4+, i was discussing them a few days ago
#asahi-dev · 2026-07-03 09:41
StanfordAppliedCyber[m]re: memory mappings, let me think about that, i'm not convinced, though it is currently 2am and my brain isn't functional
#asahi-dev · 2026-07-03 09:31
StanfordAppliedCyber[m]^ it turns out i don't need hardware breakpoints after all
#asahi-dev · 2026-07-03 09:18
StanfordAppliedCyber[m]whereas because i'm emulating sptm i can just always return a NC page for all mappings
#asahi-dev · 2026-07-03 09:17
StanfordAppliedCyber[m]virtualized sptm i think this is a fatal error that we can't get around without some intensive surgery on the sptm binary, which also defeats the point of virtualizing it
#asahi-dev · 2026-07-03 09:17
StanfordAppliedCyber[m]this wouldn't be possible if we were to virtualize sptm btw
#asahi-dev · 2026-07-03 09:15
StanfordAppliedCyber[m]turns out you cant have cache issues if you simply never cache things :)
#asahi-dev · 2026-07-03 09:10
StanfordAppliedCyber[m]got 10 boots in a row without the type 24 fabric access violation returning
#asahi-dev · 2026-07-03 09:10
StanfordAppliedCyber[m]my horrible bump allocator works
#asahi-dev · 2026-07-03 09:10
StanfordAppliedCyber[m]well i managed to sidestep the custom gxf instruction
#asahi-dev · 2026-07-03 07:04
StanfordAppliedCyber[m]literally just set a hardware breakpoint on the kernelcache location that retypes pages to page table, and then we grab a new page that's marked NC from the start and just give xnu that
#asahi-dev · 2026-07-03 07:02
StanfordAppliedCyber[m]this is some of the dumbest code of my life
#asahi-dev · 2026-07-03 07:02
StanfordAppliedCyber[m]i'm literally writing a bump allocator of noncachable pages right now
#asahi-dev · 2026-07-03 06:31
StanfordAppliedCyber[m]if you're fine with jumping on a grenade for us there actually is something that i think could be helpful for the gpu side, to be clear though it would immediately taint you and prevent you from ever writing gpu code (at least kernel level) even if you want to
#asahi-dev · 2026-07-03 06:26
StanfordAppliedCyber[m]since it's hard to trust their code and it's usually crap anyways, writing docs would actually be useful as long as they're 90% accurate and not tainted
#asahi-dev · 2026-07-03 06:25
StanfordAppliedCyber[m]this would actually be a good use of all the llm people who keep coming around lol
#asahi-dev · 2026-07-03 06:16
StanfordAppliedCyber[m]feels like that would save a lot of effort
#asahi-dev · 2026-07-03 06:16
StanfordAppliedCyber[m]honestly for times like these i just wish we had a dedicated tainted dev to jump on the grenade, just look at the firmware/kext, and return us a struct
#asahi-dev · 2026-07-02 08:19
StanfordAppliedCyber[m]best of luck soldier, don't let the mac win
#asahi-dev · 2026-07-02 08:14
StanfordAppliedCyber[m]for my actual work unfortunately x86 is nonnegotiable
#asahi-dev · 2026-07-02 08:13
StanfordAppliedCyber[m]appreciate the advice though
#asahi-dev · 2026-07-02 08:13
StanfordAppliedCyber[m]i was just gonna make a nice initrd with all the utilities i'd need
#asahi-dev · 2026-07-02 08:13
StanfordAppliedCyber[m]yeah i'm not, i don't care about actually using linux on these
#asahi-dev · 2026-07-02 08:12
StanfordAppliedCyber[m]neat
#asahi-dev · 2026-07-02 08:11
StanfordAppliedCyber[m]i'm currently talking to you over an rdp session
#asahi-dev · 2026-07-02 08:10
StanfordAppliedCyber[m]for weird logistical reasons it's rare i get hands on time with the mac so the dev workflow si remote
#asahi-dev · 2026-07-02 08:10
StanfordAppliedCyber[m]i'ma need to figure out how it works shortly
#asahi-dev · 2026-07-02 08:10
StanfordAppliedCyber[m]yeah, that's what i plan to do
#asahi-dev · 2026-07-02 08:10
StanfordAppliedCyber[m]is that marcan's "world's stupidest vuart" file?
#asahi-dev · 2026-07-02 08:09
StanfordAppliedCyber[m]i presume so
#asahi-dev · 2026-07-02 08:09
StanfordAppliedCyber[m]is there an easy way to pop a serial shell on linux over the uart?
#asahi-dev · 2026-07-02 08:09
StanfordAppliedCyber[m]how does the linux dev loop work? like just stream the kernel to m1n1 every test?
#asahi-dev · 2026-07-02 08:04
StanfordAppliedCyber[m]just the gpu tile is bigger?
#asahi-dev · 2026-07-02 08:04
StanfordAppliedCyber[m]the cpu tile on m5 pro and max is the same right?
#asahi-dev · 2026-07-02 08:04
StanfordAppliedCyber[m]knock wood no m3 pro vs max situation :)
#asahi-dev · 2026-07-02 07:59
StanfordAppliedCyber[m]we're privileged enough to have budget for interesting projects like this, even though it's not our main focus
#asahi-dev · 2026-07-02 07:58
StanfordAppliedCyber[m]stanford applied cyber is a stanford club focused on cybersecruity
#asahi-dev · 2026-07-02 07:58
StanfordAppliedCyber[m]got my club to pay for one
#asahi-dev · 2026-07-02 07:58
StanfordAppliedCyber[m]used on ebay
#asahi-dev · 2026-07-02 07:55
StanfordAppliedCyber[m]comes in the next 2 weeks
#asahi-dev · 2026-07-02 07:55
StanfordAppliedCyber[m]great, i just bought a m5 so i'ma look at that first :)
#asahi-dev · 2026-07-02 07:54
StanfordAppliedCyber[m]like there's a lot of craziness, but i've been able to solve most of my issues save for smp and debugusb
#asahi-dev · 2026-07-02 07:54
StanfordAppliedCyber[m]tbh the a18 isn't that crazy
#asahi-dev · 2026-07-02 07:54
StanfordAppliedCyber[m]what other fun stuff is in m5 pro/max?
#asahi-dev · 2026-07-02 07:53
StanfordAppliedCyber[m]thread?
#asahi-dev · 2026-07-02 07:53
StanfordAppliedCyber[m]whats the radio chip used for?
#asahi-dev · 2026-07-02 07:52
StanfordAppliedCyber[m]not have fun with a fully custom driver

plus ›