Monday, 2021-12-13

*** openpowerbot_ <openpowerbot_!~openpower@94-226-188-34.access.telenet.be> has quit IRC08:05
*** openpowerbot_ <openpowerbot_!~openpower@94-226-188-34.access.telenet.be> has joined #microwatt08:12
openpowerbot_[mattermost] <lkcl> mmor.. eevnin Paul.  quick question: what bit can be set when an exception (0x400) occurs to stop icache.vhdl from leaving fetch_failed permanently high?12:50
openpowerbot_[mattermost] <lkcl> fetch_failed is a latched register that, on *successful* completion of the MMU-PTE-lookup with itlb done, i see it drops automatically when the instruction fetch is retried12:51
openpowerbot_[mattermost] <lkcl> but what about when that PTE lookup *fails*?12:52
openpowerbot_[mattermost] <lkcl> yes, first unit test i wrote, of course it tries to execute memory at 0x00000000 in PR=1 mode, so the MMU lookup throws an invalid exception, which raises a 0x400 exception...12:53
openpowerbot_[mattermost] <lkcl> but fetch_failed is still raised HI even when executing the TRAP operation.  and only stays HI when i pull a full system reset for the next unit test :)12:53
openpowerbot_[mattermost] <lkcl> so i'm wondering which signal in icache.vldi fetch-in to pull to get it to calm down on the attention-grabbing :)12:54
openpowerbot_[mattermost] <lkcl> found something that looks like what i need: icache.flush_in18:10
openpowerbot_[mattermost] <lkcl> but... that appears to be tied to... writeback.vhdl? ehn? :)18:14
openpowerbot_[mattermost] <lkcl> ahh which is tied to redirect18:15
openpowerbot_[mattermost] <lkcl> which in turn is tied to interrupts18:15
openpowerbot_[mattermost] <lkcl> which include exceptions18:15
openpowerbot_[mattermost] <lkcl> which is indeed exactly what i want :)18:15
openpowerbot_[slack] <Paul Mackerras> right 🙂21:27

Generated by irclog2html.py 2.17.1 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!