#asahi-dev · 2022-09-08 13:10
skmp__yea that's what I'm afraid there#asahi-dev · 2022-09-08 13:10
skmp__that's the nature of it#asahi-dev · 2022-09-08 13:10
skmp__you write it now, delete it tomorrow#asahi-dev · 2022-09-08 13:10
skmp__code is ephemeral anyway#asahi-dev · 2022-09-08 13:09
skmp__the politics make it hard#asahi-dev · 2022-09-08 13:09
skmp__it's been like that for a long time now#asahi-dev · 2022-09-08 13:09
skmp__Tech is easy man#asahi-dev · 2022-09-08 13:09
skmp__that reminds me I need to notify someone about that signal handling bug I found#asahi-dev · 2022-09-08 13:09
skmp__a bit love for gotos and labels but oh well#asahi-dev · 2022-09-08 13:09
skmp__for the most part#asahi-dev · 2022-09-08 13:09
skmp__it's pretty easy to understand, simple code#asahi-dev · 2022-09-08 13:08
skmp__mostly to work around kernel bugs#asahi-dev · 2022-09-08 13:08
skmp__i've read large parts#asahi-dev · 2022-09-08 13:08
skmp__yeah#asahi-dev · 2022-09-08 13:08
skmp__have you seen what is involved in the emulation side?#asahi-dev · 2022-09-08 13:07
skmp__rather than this#asahi-dev · 2022-09-08 13:07
skmp__and after 16 hours of emulator programming, i'd rather chillax with some easy kernel work#asahi-dev · 2022-09-08 13:07
skmp__so we'll have to dive into the kernel#asahi-dev · 2022-09-08 13:07
skmp__as it won't work for all solutions anyway#asahi-dev · 2022-09-08 13:07
skmp__but doing it in userspace is a waste of time as well#asahi-dev · 2022-09-08 13:07
skmp__uh, maybe#asahi-dev · 2022-09-08 13:06
skmp__not discussing how we got into this mess#asahi-dev · 2022-09-08 13:06
skmp__the point is getting this in front of the users atm#asahi-dev · 2022-09-08 13:06
skmp__but anyways#asahi-dev · 2022-09-08 13:06
skmp__Well, one could say that says more about the kernel, than the feature#asahi-dev · 2022-09-08 13:05
skmp__if so, a boot option is the best 'hack' right now#asahi-dev · 2022-09-08 13:05
skmp__marcan: so it is not a strict hardware limit?#asahi-dev · 2022-09-08 13:05
skmp__:p#asahi-dev · 2022-09-08 13:05
skmp__I member#asahi-dev · 2022-09-08 13:04
skmp__everyone just used 'whatever was best'#asahi-dev · 2022-09-08 13:04
skmp__microsoft used 1K for wince#asahi-dev · 2022-09-08 13:04
skmp__IBM always used random page sizes#asahi-dev · 2022-09-08 13:04
skmp__@mps that's how it used to be up to early 2000s#asahi-dev · 2022-09-08 13:04
skmp__@jannau The iommu has 4k page support?#asahi-dev · 2022-09-08 13:03
skmp__(because it holds 4x as much mapped area)#asahi-dev · 2022-09-08 13:03
skmp__and 16K is just so much more power efficient at the tlb cache level#asahi-dev · 2022-09-08 13:02
skmp__4k is too small for the amount of ram we have#asahi-dev · 2022-09-08 13:02
skmp__apple is right there#asahi-dev · 2022-09-08 13:02
skmp__plus, 16k is the right size#asahi-dev · 2022-09-08 13:02
skmp__it's only been standard for a decade or so at best#asahi-dev · 2022-09-08 13:02
skmp__well, 4k standar page size isn't really a 'standard'#asahi-dev · 2022-09-08 13:01
skmp__rotfl#asahi-dev · 2022-09-08 13:01
skmp__no one likes that narative#asahi-dev · 2022-09-08 13:01
skmp__'ubuntu is 10% slower than osx - apple is right osx is best'#asahi-dev · 2022-09-08 13:01
skmp__branding wise, it will look really bad#asahi-dev · 2022-09-08 13:01
skmp__maybe#asahi-dev · 2022-09-08 13:00
skmp__which, technically it is, because i'm providing the vm#asahi-dev · 2022-09-08 13:00
skmp__I'm an emulator author, my job is to predict how people will misasume things and then it'll end up on my bug tracker as a bug on my project#asahi-dev · 2022-09-08 12:59
skmp__oh possibly#asahi-dev · 2022-09-08 12:59
skmp__and, m1 takes a big (iirc 12%ish) perf hit from using 4k pages, so it will be very hard to convince a distro to do that