09:50 emersion: does anyone have a good list of ftrace points for nouveau?
09:50 emersion: i'm looking for something like these https://github.com/mikesart/gpuvis/blob/master/sample/trace-cmd-start-tracing.sh#L24
09:52 karolherbst: not really. I think some of the ioctls functions would be useful to have though
10:25 emersion: hm
10:25 emersion: i'm getting 20k IO_PAGE_FAULT warnings in my dmesg…
10:25 emersion: i wonder what could be the cause
10:36 kwizart: emersion, which kernel version for the record ?
10:36 emersion: 5.11.6
10:36 emersion: but i'm trying to do things like amd→nouveau dmabuf transfers
10:37 emersion: those just stall for seconds
10:38 kwizart: interesting, I have page fault on jetson (so nouveau->tegra) reported at https://bugzilla.redhat.com/show_bug.cgi?id=1937129
10:38 kwizart: with anything newer than 5.11-rc1
10:39 kwizart: (and bissection pointing to 461619f5c3242aaee9ec3f0b7072719bd86ea207] drm/nouveau: switch to new allocator)
10:39 kwizart: btw I cannot revert this commit easily on top of current 5.11
10:40 emersion: it's not just a page fault you're experiencing, it's a bug when nouveau handles page faults
10:41 emersion: i just have the page faults, without the nouveau bug
13:53 emersion: hmm, NOUVEAU_GEM_PUSHBUF is taking like 9s
14:01 kwizart: emersion, have you tried 5.11-stable-rc ? https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git/log/?h=queue/5.11
14:01 kwizart: emersion, there are 2 interesting patches (on on nouveau, the other on mm)
14:01 kwizart: drm/ttm actually
14:02 emersion: this isn't due to a kernel upgrade or anything
14:08 emersion: bleh, i don't understand any of this stuff
15:00 nzamb1: Hi All, my Linux is constantly freezing because of nouveau driver. I have pasted a log some time ago. I dunno if someone had a chance to have a look. I'm getting following error: https://pastebin.com/a8w9dGpC
15:00 nzamb1: I'm running ubuntu 20.04
15:00 nzamb1: it's very annoying that the system freezing
15:00 imirkin: nzamb1: the top is cut off
15:01 nzamb1: I don't understand you
15:01 imirkin: the message is longer than what you indicated
15:02 imirkin: you didn't include the start of it
15:02 nzamb1: ok just a moment
15:06 nzamb1: https://pastebin.com/Ax48WPwY
15:06 nzamb1: should be better now
15:07 imirkin: nzamb1: is the order of the lines in this log inverted somehow?
15:08 imirkin: ah yes, it is. that's why the trace looks backwards.
15:08 imirkin: that makes a _lot_ more sense now
15:08 nzamb1: journalctl -r
15:08 nzamb1: sorry
15:09 nzamb1: yes it's inverted. I can paste without -r if needed
15:09 imirkin: unfortunately i have no idea what would cause this
15:09 imirkin: can you file a bug here, and make sure to include a "regular" order version of that log? https://gitlab.freedesktop.org/drm/nouveau/-/issues
15:10 nzamb1: ok. Thank you. I'll create a bug
15:32 nzamb1: imirkin https://gitlab.freedesktop.org/drm/nouveau/-/issues/78
15:32 imirkin: nzamb1: please include the output of `lspci -nn -d 10de:`
15:33 imirkin: (which should indicate which GPU you have)
15:34 nzamb1: done
15:35 imirkin: interesting. 2 GPUs...
15:35 imirkin: heh, FX 4800. does it sound like you're sitting on a jet engine?
15:37 nzamb1: something like that but freezing GT218 [GeForce 210]
15:37 imirkin: heh
15:38 imirkin: are there monitors connected to both? which is set as primary?
15:38 nzamb1: monitors connected to booth and I'm running multi seat setup
15:39 nzamb1: mykola@k-workstation:~$ loginctl
15:39 nzamb1:      c4 1000 mykola seat0
15:39 nzamb1:      c8 1001 svetlana seat1
15:39 imirkin: i'm largely unfamiliar with how multi-seat actually works in practice
15:39 imirkin: does each seat get a GPU?
15:39 imirkin: or a random collection of outputs?
15:39 nzamb1: exactly
15:40 nzamb1: each seat get a GPU
15:40 nzamb1: 1 GPU per 1 seat
15:40 imirkin: like could a seat get HDMI-1 from gpu 1, and DVI-D-1 from gpu 2, while another gets DVI-D-2 from gpu1 and HDMI-2 from gpu2?
15:40 imirkin: or it's at a "whole card" level?
15:40 karolherbst: imirkin: https://gitlab.freedesktop.org/drm/nouveau/-/issues/78 this is fixed, right?
15:40 imirkin: (or you just happen to have done it at the whole card level)
15:41 nzamb1: it's a "whole card" level
15:41 imirkin: karolherbst: i have no clue what the issue is
15:41 imirkin: which is why i told him to file a bug
15:41 karolherbst: ohhh right
15:41 karolherbst: the other vfree thingy was something else.. ehh
15:41 imirkin: perhaps it's fixed - i dunno
15:41 imirkin: the other thing was kzalloc failing, and for pre-nv50
15:41 imirkin: speaking of ... when is skeggsb_ back?
15:42 karolherbst: next week
15:42 karolherbst: I will talk with him what to do about trivial patches anyway. My plan is to convince him that we can just randomly merge smaller things
15:42 nzamb1: if you have a fix and you can give it to me the I can test it
15:43 imirkin: karolherbst: kk
15:43 imirkin: nzamb1: i think karolherbst got confused with another unrelated issue which i fixed recently
15:44 imirkin: we don't know what the problem is, at this point
22:52 Lyude: mupuf, skeggsb_, jcline, imirkin - igt changes are on igt-dev/nouveau ml btw, about to send out the kernel side stuff as well