ChanServ changed the topic of #etnaviv to: #etnaviv - the home of the reverse-engineered Vivante GPU driver - Logs https://oftc.irclog.whitequark.org/etnaviv
pcercuei has quit [Quit: dodo]
frieder has joined #etnaviv
lynxeye has joined #etnaviv
mvlad has joined #etnaviv
mvlad has quit [Remote host closed the connection]
f_ has joined #etnaviv
mvlad has joined #etnaviv
pcercuei has joined #etnaviv
f_ has quit [Quit: To contact me, PM f_[xmpp] or send an email. See https://vitali64.duckdns.org/.]
pjakobsson_ has joined #etnaviv
pjakobsson has quit [Ping timeout: 480 seconds]
<bl4ckb0ne> lynxeye: do you know why the mtlb can only point to a 32 bit base address of a stlb? the galcore driver sets both dma mask and coherent mask to 40
<lynxeye> bl4ckb0ne: the mtlb doesn't support the same trick as the stlb, where the upper 8 bits are squashed in the lower pagetable bits. So there just is no way to point to a 40bit stlb page from the mtlb.
<lynxeye> At least as far as I know. I have not found any indication in the downstream driver that the mtlb supports this trick.
<bl4ckb0ne> there's a gcdENABLE_40BIT_VA define, might be that
<bl4ckb0ne> thanks
<bl4ckb0ne> im still poking around for that mmu fault/hang, double checking everything and trying to understand the driver
<bl4ckb0ne> i suspect the mmu fault being from the cmd buffer that's submitted, if I use the user_size instead of the size for the link_dwords i dont get the fault but get more hangs
f_ has joined #etnaviv
frieder has quit [Remote host closed the connection]
lynxeye has quit [Quit: Leaving.]
funderscore has joined #etnaviv
f_ has quit [Ping timeout: 480 seconds]
funderscore is now known as f_
f_ has quit [Quit: To contact me, PM f_[xmpp] or send an email. See https://vitali64.duckdns.org/.]
mvlad has quit [Remote host closed the connection]
pcercuei has quit [Quit: brb]
pcercuei has joined #etnaviv
pcercuei has quit [Quit: dodo]