#
#asahi-re · 2026-07-21 19:56
sveni think even GXR/SPRR but that doesn't help us because host-XNU already drives all the hardware and won't expose it to us
#asahi-re · 2026-07-21 19:56
svenallows you to run EL1 guests from XNU with some additional apple features enabled
#asahi-re · 2026-07-21 19:55
enverbalalicbtw, do we know what csrutil allow-research-guests does, according to apple it's some virtual research environment for private cloud compute, and enabling that allows additional access to hardware ?
#asahi-re · 2026-07-21 19:55
svenoh, and you need to write to HCR to enable EL1 anyway
#asahi-re · 2026-07-21 19:55
yukaAhh fair
#asahi-re · 2026-07-21 19:54
svenand SPTM will probably make sure that you can't setup stage 2 translations, etc.
#asahi-re · 2026-07-21 19:53
svenyou e.g. can't write to HCR from EL2 the moment GXF is enabled
#asahi-re · 2026-07-21 19:49
yukaor does SPTM not allow setting up the pagetables that way
#asahi-re · 2026-07-21 19:49
yukais that just how macOS does it, or does the normal EL2/EL1 separation just not work?
#asahi-re · 2026-07-21 19:45
sventhe latter
#asahi-re · 2026-07-21 19:45
yukaI don't know if the SPTM guest can even have its own guests, or if everything virtualization shaped needs to go via SPTM
#asahi-re · 2026-07-21 19:44
svenyeah
#asahi-re · 2026-07-21 19:44
djI just wanna see if the problem is rly lying in iboot or sptm layer and conclude my experiment
#asahi-re · 2026-07-21 19:43
svenah
#asahi-re · 2026-07-21 19:43
djwording is off but I meant the experiment to run m1n1 under SPTM :)
#asahi-re · 2026-07-21 19:43
svenuh, what do you mean with sptm enabled m1n1?
#asahi-re · 2026-07-21 19:42
djI’m gonna try emulating more of sptm first, and later today boot back into macOS and try a sptm enabled m1n1
#asahi-re · 2026-07-21 19:42
djI suppose it would make things easier
#asahi-re · 2026-07-21 19:42
enverbalalictheoretically, would a m1n1 macho running under SPTM allow the macos virtualization to run without the sptm emulation hacks ?
#asahi-re · 2026-07-21 19:42
svenmight be interesting either way for some experiments
#asahi-re · 2026-07-21 19:41
svensure, but keep in mind that running m1n1 under SPTM is going to be quite annoying
#asahi-re · 2026-07-21 19:41
djand if it _just works_, we know where the problem is
#asahi-re · 2026-07-21 19:41
djbut for an experiment to see if secondaries work under SPTM, would be a cool verification method no?
#asahi-re · 2026-07-21 19:40
djlol fair, that’s ruled out then
#asahi-re · 2026-07-21 19:40
svenyou're definitely not running under sptm unless you specifically adjusted m1n1 :)
#asahi-re · 2026-07-21 19:39
svensptm owns the pagetables and you have to nicely ask it if you want to change any
#asahi-re · 2026-07-21 19:39
svenwe can't run linux under sptm
#asahi-re · 2026-07-21 19:39
djt*
#asahi-re · 2026-07-21 19:39
djI don’t think it’s running under SPTM right now. But if I could try doing that, could possibly make things easier for f6050
#asahi-re · 2026-07-21 19:38
svenmight even be easier to fork m1n1 and adjust it to be able to run under SPTM for experiments
#asahi-re · 2026-07-21 19:38
yuka💯
#asahi-re · 2026-07-21 19:38
yukayeah, so it would be nice if someone had a closer look at that boot mode, but it's probably not an easy task
#asahi-re · 2026-07-21 19:38
svenand m1n1 will probably panic very early when it tries to access the uart. and even if that worked it'll definitely panic when trying to enable the MMU
#asahi-re · 2026-07-21 19:37
svenit won't even allow the m1n1 macho to be installed right now because it doesn't look like xnu anymore :D
#asahi-re · 2026-07-21 19:37
yukaor even get m1n1 running fully
#asahi-re · 2026-07-21 19:37
yukaI haven't verified any of this, but if you actually run under SPTM it might be very annoying to even get debug output in any way
#asahi-re · 2026-07-21 19:36
yukabecause that's pretty much how you install m1n1 nowadays, and the assumption is if you attempted to install the macho version on recent platforms you would be dropped into an environment running under SPTM
#asahi-re · 2026-07-21 19:36
yukaI assume you have been doing the raw boot object path
#asahi-re · 2026-07-21 19:35
djthat makes more sense then, I didn’t know this has been the case before with M4. and the lock down on a lot of stuff is real. is it possible for me to test stuff out with raw boot objects?
#asahi-re · 2026-07-21 19:32
svenand then they didn't test anything 🙃
#asahi-re · 2026-07-21 19:32
yukathere is a lot of reasons to assume this is an iboot bug, though it is somewhat difficult to prove (but your analysis with reading pc of the secondary cores kinda supports it)
#asahi-re · 2026-07-21 19:31
yukadj: for context, on the base M4 model there was also specific macOS/iboot versions which had broken smp (possibly in a similar way) and then it worked again just like that after one with 26.x updates
#asahi-re · 2026-07-21 19:31
svenafaict on M4+ they at least have some way to configure which sysregs are read-only and i think they just disabled everything except what's in the arm architecture reference manual
#asahi-re · 2026-07-21 19:30
yukawhat is locked where is a bit unknown, but things are definitely locked down a lot
#asahi-re · 2026-07-21 19:30
yukaright
#asahi-re · 2026-07-21 19:30
sveni don't think the silicon is there on M3 to actually lock anything down
#asahi-re · 2026-07-21 19:29
yuka*or with the non-raw / macho kernel objects on M4+
#asahi-re · 2026-07-21 19:29
yukaI personally haven't verified if this is also the case when using a newer iboot (one from an SPTM-enabled build) on an M3 device, or with the non-raw / macho kernel objects
#asahi-re · 2026-07-21 19:28
yukathere are things which are known to be locked (though not under which specific conditions?), like pretty much all apple specific imp regs / msrs on the usual setup (install raw boot object via kmutil -r) on M4
#asahi-re · 2026-07-21 19:27
yuka> <sven> and the fuos path needs to somehow lock down all sysregs, etc.

plus ›