ChanServ changed the topic of #asahi-dev to: Asahi Linux: porting Linux to Apple Silicon macs | Non-development talk: #asahi | General development | GitHub: https://alx.sh/g | Wiki: https://alx.sh/w | Logs: https://alx.sh/l/asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
sam_- has quit []
<ChaosPrincess>
Idk, maybe. The mipi im talking about is the one used to connect the touchbar screen.
sam_ has joined #asahi-dev
kettenis_ has quit [Ping timeout: 480 seconds]
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
Thsf has joined #asahi-dev
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
A_L_I_C_E has quit [Remote host closed the connection]
deteg1337 has joined #asahi-dev
Swiftloke has quit [Quit: ABANDON SHIP!]
Swiftloke has joined #asahi-dev
Thsf has quit [Ping timeout: 480 seconds]
raveling has quit [Ping timeout: 480 seconds]
<marcan>
if it has a dart yeah, known problem
<marcan>
just work around it for now
<marcan>
I'll fix this in core code at some point
<marcan>
it's biting us everywhere, moreso since 6.2
<marcan>
ChaosPrincess: ^
<marcan>
jannau: yes, DART probing first is what causes it
<marcan>
this needs to be fixed in core genpd code to refuse to power down any PDs that have fwlinks to devices that haven't probed yet if they were on at boot time
<marcan>
that's the only sane solution here
<marcan>
ChaosPrincess: just mark the relevant PDs as apple,always-on; for now
<marcan>
CoolStar: webcam is behind a giant firmware blob so it doesn't matter much what link it uses behind the scenes
<marcan>
I think the socs support MIPI and DP
darkapex1 has quit []
darkapex has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
<CoolStar>
marcan: I see; I guess even if it's MIPI, yeah it doesn't matter if the CIO2 and IPU are both on the same controller (unlike Intel where it's separate)
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
newiz has joined #asahi-dev
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
A_L_I_C_E has joined #asahi-dev
<marcan>
CoolStar: in general you can access the hardware directly if you want, but all of Apple's coprocessors also access the hardware they are responsible for directly and expect to do so
<marcan>
so unless we're bypassing firmware (which I'm very reluctant to do, both because then we don't have a consistent RE story and because firmware usually helps upwards compat), we don't have to care
<marcan>
I think the only case where we've had a plausible "byassing firmware is OK" story so far is ANE, though I still have my doubts about that one
deteg1337 has quit [Ping timeout: 480 seconds]
<chadmed_>
R and Jamie were going down a path of doing so with AV{D,E} too
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
chadmed_ has quit [Remote host closed the connection]
cylm has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
chadmed_ has joined #asahi-dev
<marcan>
AVD I can see yeah, AVE I'm not so sure
deteg1337 has quit [Ping timeout: 480 seconds]
kedde has quit [Ping timeout: 480 seconds]
deteg1337 has joined #asahi-dev
deteg1337 has quit [Ping timeout: 480 seconds]
kedde has joined #asahi-dev
chadmed_ has quit [Quit: Page closed]
chipxxx has joined #asahi-dev
chipxxx has quit [Remote host closed the connection]
chipxxx has joined #asahi-dev
deteg1337 has joined #asahi-dev
deteg1337 has quit []
<sven>
fwiw, technically pcie should be a clock controller and dart should have that APPCLK as a dependency
<sven>
it doesn’t matter for the pcie darts so far because appclk is already enabled inside m1n1
newiz has quit [Quit: Konversation terminated!]
kettenis has joined #asahi-dev
bps has joined #asahi-dev
<CoolStar>
marcan: yeah understandable given there can be performance penalties from bypassing coprocessors (I tried bitbanging I2S on Skylake once -- it didn't look pretty in terms of how inefficient it was)
<ChaosPrincess>
these machines do not have it, but on x86 dont you also have a problem that smm might come and say hello, and break all your timings.
<CoolStar>
ChaosPrincess: yes, but the machines I've dealt with run coreboot so SMM is fairly minimal
i509vcb has quit [synthon.oftc.net weber.oftc.net]
nafod has quit [synthon.oftc.net weber.oftc.net]
Hibyehello_ has quit [synthon.oftc.net weber.oftc.net]
richyliu2 has quit [synthon.oftc.net weber.oftc.net]
skipwich has quit [synthon.oftc.net weber.oftc.net]
nopeslide13 has quit [synthon.oftc.net weber.oftc.net]
compassion has quit [synthon.oftc.net weber.oftc.net]
systwi has quit [synthon.oftc.net weber.oftc.net]
Chainsaw has quit [synthon.oftc.net weber.oftc.net]
snek has quit [synthon.oftc.net weber.oftc.net]
Puto has quit [synthon.oftc.net weber.oftc.net]
elvishjerricco has quit [synthon.oftc.net weber.oftc.net]
amada95 has quit [synthon.oftc.net weber.oftc.net]
cptcobalt has quit [synthon.oftc.net weber.oftc.net]
enron has quit [synthon.oftc.net weber.oftc.net]
rbenua has quit [synthon.oftc.net weber.oftc.net]
azenla has quit [synthon.oftc.net weber.oftc.net]
cds has quit [synthon.oftc.net weber.oftc.net]
supay has quit [synthon.oftc.net weber.oftc.net]
dubiousness has quit [synthon.oftc.net weber.oftc.net]
tom-w has quit [synthon.oftc.net weber.oftc.net]
krbtgt has quit [synthon.oftc.net weber.oftc.net]
coder_kalyan has quit [synthon.oftc.net weber.oftc.net]
jabashque_ has quit [synthon.oftc.net weber.oftc.net]
qyousef has quit [synthon.oftc.net weber.oftc.net]
jesse-s has quit [synthon.oftc.net weber.oftc.net]
djorz has quit [synthon.oftc.net weber.oftc.net]
cafebabe has quit [synthon.oftc.net weber.oftc.net]
opticron has quit [synthon.oftc.net weber.oftc.net]
psanford has quit [synthon.oftc.net weber.oftc.net]
skippypaws has quit [synthon.oftc.net weber.oftc.net]
d4ve has quit [synthon.oftc.net weber.oftc.net]
handlerug has quit [synthon.oftc.net weber.oftc.net]
alethkit has quit [synthon.oftc.net weber.oftc.net]
NekomimiScience has quit [synthon.oftc.net weber.oftc.net]
khilman has quit [synthon.oftc.net weber.oftc.net]
_alice has quit [synthon.oftc.net weber.oftc.net]
mmarchini_____ has quit [synthon.oftc.net weber.oftc.net]
robher has quit [synthon.oftc.net weber.oftc.net]
jonmasters__ has quit [synthon.oftc.net weber.oftc.net]
tardyp has quit [synthon.oftc.net weber.oftc.net]
piroko has quit [synthon.oftc.net weber.oftc.net]
Manouchehri_ has quit [synthon.oftc.net weber.oftc.net]
abby has quit [synthon.oftc.net weber.oftc.net]
dk_ has quit [synthon.oftc.net weber.oftc.net]
steev has quit [synthon.oftc.net weber.oftc.net]
linxz has quit [synthon.oftc.net weber.oftc.net]
arnd has quit [synthon.oftc.net weber.oftc.net]
isinyaaa has quit [synthon.oftc.net weber.oftc.net]
eric_engestrom has quit [synthon.oftc.net weber.oftc.net]
esden has quit [synthon.oftc.net weber.oftc.net]
austriancoder has quit [synthon.oftc.net weber.oftc.net]
daniels has quit [synthon.oftc.net weber.oftc.net]
Lightsword has quit [synthon.oftc.net weber.oftc.net]
steven has quit [synthon.oftc.net weber.oftc.net]
pzc has quit [synthon.oftc.net weber.oftc.net]
lucic71 has quit [synthon.oftc.net weber.oftc.net]
hays has quit [synthon.oftc.net weber.oftc.net]
i509vcb has joined #asahi-dev
nafod has joined #asahi-dev
Hibyehello_ has joined #asahi-dev
richyliu2 has joined #asahi-dev
skipwich has joined #asahi-dev
compassion has joined #asahi-dev
nopeslide13 has joined #asahi-dev
systwi has joined #asahi-dev
elvishjerricco has joined #asahi-dev
dubiousness has joined #asahi-dev
steven has joined #asahi-dev
lucic71 has joined #asahi-dev
abby has joined #asahi-dev
alethkit has joined #asahi-dev
cds has joined #asahi-dev
amada95 has joined #asahi-dev
handlerug has joined #asahi-dev
dk_ has joined #asahi-dev
coder_kalyan has joined #asahi-dev
d4ve has joined #asahi-dev
skippypaws has joined #asahi-dev
krbtgt has joined #asahi-dev
enron has joined #asahi-dev
psanford has joined #asahi-dev
hays has joined #asahi-dev
pzc has joined #asahi-dev
Manouchehri_ has joined #asahi-dev
djorz has joined #asahi-dev
opticron has joined #asahi-dev
Lightsword has joined #asahi-dev
piroko has joined #asahi-dev
arnd has joined #asahi-dev
supay has joined #asahi-dev
Puto has joined #asahi-dev
tom-w has joined #asahi-dev
cafebabe has joined #asahi-dev
qyousef has joined #asahi-dev
jonmasters__ has joined #asahi-dev
khilman has joined #asahi-dev
daniels has joined #asahi-dev
mmarchini_____ has joined #asahi-dev
austriancoder has joined #asahi-dev
_alice has joined #asahi-dev
robher has joined #asahi-dev
esden has joined #asahi-dev
cptcobalt has joined #asahi-dev
tardyp has joined #asahi-dev
snek has joined #asahi-dev
eric_engestrom has joined #asahi-dev
jesse-s has joined #asahi-dev
azenla has joined #asahi-dev
NekomimiScience has joined #asahi-dev
linxz has joined #asahi-dev
steev has joined #asahi-dev
Chainsaw has joined #asahi-dev
isinyaaa has joined #asahi-dev
rbenua has joined #asahi-dev
jabashque_ has joined #asahi-dev
c10l has quit [Quit: Bye o/]
c10l has joined #asahi-dev
chadmed has quit [Ping timeout: 480 seconds]
chadmed has joined #asahi-dev
hightower2 has quit [Ping timeout: 480 seconds]
nyilas has joined #asahi-dev
nsklaus has joined #asahi-dev
<sven>
there might be power consumption penalties if we bypassed co-processors but I doubt we'd see a measurable performance penalty
<sven>
the biggest issues are that reverse engineering the firmware is usually much more challenging and time consuming than just reverse engineering its interface and that the firmware interface probably helps us when supporting new chip revisions
nyilas has quit [Remote host closed the connection]
nyilas has joined #asahi-dev
cylm has joined #asahi-dev
<kettenis>
speaking about firmware: I probably should work on getting the asmedia firmware loaded in u-boot
<kettenis>
that'll save me having to implement it in OpenBSD
Thsf has joined #asahi-dev
Thsf has quit [Ping timeout: 480 seconds]
nsklaus has quit [Ping timeout: 480 seconds]
<kettenis>
hmm, the m2 pro mini should not inherit the wifi bits from t600x-j375.dtsi
<eric_engestrom>
jannau: glad to know I'm not alone :]
<eric_engestrom>
was there a fix or workaround?
<jannau>
if I remembered. with hw counters you need to taskset either efficiency or performance cores
<jannau>
that said, a plain `perf record sleep 1` produces samples for me on m1 max
linuxgemini13 has quit []
linuxgemini13 has joined #asahi-dev
linuxgemini13 is now known as linuxgemini
<jannau>
does perf record -e cpu-clock ... work?
<eric_engestrom>
jannau: nope :/
<jannau>
/proc/sys/kernel/perf_event_paranoid is set to allow user event sampling?
<jannau>
somehow the blizzard pmu went missing on m2 pro
A_L_I_C_E has quit [Ping timeout: 480 seconds]
<jannau>
ah, the compatible is missing a 'z'
Stary has quit [Ping timeout: 480 seconds]
<jannau>
eric_engestrom: `perf stat sleep 1` is generally a nice way to test if perf works as expected. can you try that on both the performance and efficiency cores
<jannau>
it should work on one or the other. I'm not sure how perf/ the kernel selects which counters are cycles/instructions but it mappes only to either one
<jannau>
see perf list about which cycle and instruction counters you have
<jannau>
on m2* it's apple_avalanche_pmu/cycles/ and apple_blizzard_pmu/cycles/
Stary has joined #asahi-dev
newiz has joined #asahi-dev
A_L_I_C_E has joined #asahi-dev
kit_ty_kate3 has quit [Quit: WeeChat 3.6]
kit_ty_kate has joined #asahi-dev
<eric_engestrom>
jannau: /proc/sys/kernel/perf_event_paranoid was 2, but setting it to 0 makes no difference
<eric_engestrom>
thanks for `perf stat`, thats' much simpler than `perf record ... && perf report ...` :)
<eric_engestrom>
I'm on an m2 air
<jannau>
eric_engestrom: try -1
<eric_engestrom>
not sure why I typed 0, -1 is what I tried :]