alyssa changed the topic of #panfrost to: Panfrost - FLOSS Mali Midgard & Bifrost - Logs https://freenode.irclog.whitequark.org/panfrost - <daniels> avoiding X is a huge feature
macc24 has quit [Ping timeout: 260 seconds]
macc24 has joined #panfrost
<robclark> urjaman: IMO gpu drivers can only go so far to solve stupid.. ;-)
vstehle has quit [Ping timeout: 265 seconds]
stikonas has quit [Remote host closed the connection]
atler has quit [Ping timeout: 252 seconds]
atler has joined #panfrost
alyssa has quit [Remote host closed the connection]
kaspter has joined #panfrost
kaspter has quit [Excess Flood]
kaspter has joined #panfrost
camus has joined #panfrost
kaspter has quit [Ping timeout: 268 seconds]
camus is now known as kaspter
macc24 has quit [Quit: Connection closed]
WoC has quit [Remote host closed the connection]
anarsoul|c has joined #panfrost
WoC has joined #panfrost
ente has quit [Ping timeout: 246 seconds]
toggleton[m] has quit [*.net *.split]
clementp[m] has quit [*.net *.split]
mdrjr has quit [*.net *.split]
clementp[m] has joined #panfrost
toggleton[m] has joined #panfrost
alpernebbi has joined #panfrost
vstehle has joined #panfrost
ente has joined #panfrost
chewitt has quit [Quit: Adios!]
wwilly has joined #panfrost
camus has joined #panfrost
kaspter has quit [Ping timeout: 268 seconds]
camus is now known as kaspter
<bbrezillon> robclark: I was trying to trace weston, but it looks like eglSetDamageRegionKHR() calls are not intercepted :-(
ente has quit [Ping timeout: 240 seconds]
guillaume_g has joined #panfrost
stikonas has joined #panfrost
raster has joined #panfrost
Elpaulo has joined #panfrost
macc24 has joined #panfrost
kaspter has quit [Ping timeout: 240 seconds]
kaspter has joined #panfrost
megi has quit [Quit: WeeChat 3.1]
megi has joined #panfrost
camus has joined #panfrost
kaspter has quit [Remote host closed the connection]
camus is now known as kaspter
robmur01 has joined #panfrost
chewitt has joined #panfrost
warpme_ has joined #panfrost
chewitt has quit [Read error: Connection reset by peer]
chewitt has joined #panfrost
ente has joined #panfrost
ente has quit [Ping timeout: 240 seconds]
alyssa has joined #panfrost
ente has joined #panfrost
kaspter has quit [Ping timeout: 252 seconds]
kaspter has joined #panfrost
WoC has quit [Remote host closed the connection]
WoC has joined #panfrost
patrik has joined #panfrost
nlhowell has quit [Ping timeout: 240 seconds]
camus has joined #panfrost
kaspter has quit [Ping timeout: 240 seconds]
camus is now known as kaspter
empty_string has quit [Ping timeout: 265 seconds]
<br_> robclark: may be vulkan/opencl would be a good alternative for 25 year old opengl for kmscube ?
<br_> robclark: do you know which bits I should set in Mali page table entry for no-exec ?
<br_> it looks like io-pgtable-arm.c sets both 53 and 54
<br_> arm_lpae_prot_to_pte()
ente has quit [Ping timeout: 240 seconds]
<alyssa> robher: ^
<br_> I'm asking because Mali PTE read/write bits are compatible with Stage2 set (1 << 6) and (1 << 7) respectively
<br_> but 53 and 54 bits of Stage2 set allowing execution at EL1
<br_> so it turns out that read/write bits for Mali pte comes from Stage2, but no-exec from Stage1 set
<robmur01> br_: yes, it looks sort of like stage 1 in some places, sort of like stage 2 in others, but is really neither :)
<robmur01> technically we shouldn't set bit 53 for Mali, since it's reserved...
<alyssa> "reserved"
<br_> robmur01: ok, if only 54 bit is needed for no-exec, then it looks all Stage2 based on macroses in freebsd
chewitt has quit [Read error: Connection reset by peer]
<robmur01> yes, permissions are S2-ish, while it's the attributes that are S1-ish
<br_> ah ok
<br_> thanks!
chewitt has joined #panfrost
camus has joined #panfrost
kaspter has quit [Ping timeout: 252 seconds]
camus is now known as kaspter
kaspter has quit [Ping timeout: 240 seconds]
kaspter has joined #panfrost
guillaume_g has quit [Quit: Konversation terminated!]
empty_string has joined #panfrost
ente has joined #panfrost
endrift has quit [Read error: Connection reset by peer]
endrift has joined #panfrost
raster has quit [Quit: Gettin' stinky!]
alpernebbi has quit [Quit: alpernebbi]
wwilly has quit [Quit: This computer has gone to sleep]
warpme_ has quit [Quit: Connection closed for inactivity]
<HdkR> Oh
<HdkR> alyssa: btw, gfxbench works in FEX now
<macc24> HdkR: as if there are panfrost boards that can run fex
<HdkR> The GoA and Go Super can, just won't be a fun experience :P
<italove> what is FEX?
<HdkR> x86/x86-64 Linux userspace emulator for AArch64, ARMv8.1+
<italove> ty
<alyssa> HdkR: \o/
alyssa has quit [Remote host closed the connection]
alyssa has joined #panfrost
<alyssa> HdkR: cortex A73 is too old I guess?
<HdkR> I still need to fix unaligned atomics there sadly
<HdkR> If you're super lucky the application may not use them but it is unlikely
<alyssa> :(
<HdkR> I'm too busy wiring up 32-bit emulation bits to get back to it
<macc24> alyssa: mt8192 would be compatible... when it releases
<macc24> HdkR: isn't A35 just armv8.0?
<HdkR> Oh right, it is
<HdkR> I was thinking A55 for some reason
<macc24> i wis it was a55
<macc24> wish*
<HdkR> I was thinking about the C4 SoC :D
<macc24> if only it as in handheld form factor
pendingchaos has quit [Ping timeout: 252 seconds]
pendingchaos has joined #panfrost