#
…

2026-08-12

00:02hdbngr has quit [Ping timeout: 480 seconds]
00:08hdbngr has joined #asahi-dev
00:15RafayUghh, that forcing 0x413 is breaking link init/training and therefore I am getting USB 2 speeds.
00:17hdbngr has quit [Ping timeout: 480 seconds]
00:27Rafay_ has joined #asahi-dev
00:36hdbngr has joined #asahi-dev
00:49rany has quit [Remote host closed the connection]
00:49rany has joined #asahi-dev
00:51hdbngr has quit [Ping timeout: 480 seconds]
00:52hdbngr has joined #asahi-dev
01:12hdbngr has quit [Ping timeout: 480 seconds]
01:35rany has quit [Ping timeout: 480 seconds]
01:35rany has joined #asahi-dev
02:00yurix has quit [Remote host closed the connection]
02:00yurix has joined #asahi-dev
02:13hdbngr has joined #asahi-dev
02:18halloy1935 has joined #asahi-dev
02:19gargantua has joined #asahi-dev
02:21hdbngr has quit [Ping timeout: 480 seconds]
02:25gargantua has quit []
03:01hdbngr has joined #asahi-dev
03:02tjemke774 has joined #asahi-dev
03:07tjemke77 has quit [Ping timeout: 480 seconds]
03:07tjemke774 is now known as tjemke77
03:10hdbngr has quit [Ping timeout: 480 seconds]
03:10mripard has quit [Remote host closed the connection]
03:11mripard has joined #asahi-dev
03:32hdbngr has joined #asahi-dev
03:36luma_ has joined #asahi-dev
03:37luma has quit [Ping timeout: 480 seconds]
03:38luma_ is now known as luma
03:40hdbngr has quit [Ping timeout: 480 seconds]
03:52chadmed[ 184.342412] apple-dcp 289c00000.dcp: RTKit: syslog message: PPipeDCP_H13P.cpp:10259: IOMFB: polarity stuck! Resetting display
03:53chadmedall i want is an interchange buffer smdh
03:56nora_ has joined #asahi-dev
03:58nora has quit [Ping timeout: 480 seconds]
04:04hdbngr has joined #asahi-dev
04:07__Tetris__ has quit [Quit: Ping timeout (120 seconds)]
04:07__Tetris__ has joined #asahi-dev
04:07NekomimiScience has quit [Read error: Connection reset by peer]
04:08NekomimiScience has joined #asahi-dev
04:13hdbngr has quit [Ping timeout: 480 seconds]
04:28halloy1935 has quit [Ping timeout: 480 seconds]
04:37svenrafay: what makes you think it breaks anything? that looks good actually
04:44sventhe only error i see is "[ 65.440040] thunderbolt-apple-acio 501ac0000.nhi: RTKit: syslog message: high_speed_lane.c:289: Gen2/3 link error. lane=1, error=88" and i got that locally as well which made me suspect that something with lane bonding goes wrong yesterday
05:00hdbngr has joined #asahi-dev
05:08hdbngr has quit [Ping timeout: 480 seconds]
05:31hdbngr has joined #asahi-dev
05:40hdbngr has quit [Ping timeout: 480 seconds]
05:44hdbngr has joined #asahi-dev
05:53hdbngr has quit [Ping timeout: 480 seconds]
05:57LarstiQ has joined #asahi-dev
06:05hdbngr has joined #asahi-dev
06:14hdbngr has quit [Ping timeout: 480 seconds]
06:24rany has quit [Remote host closed the connection]
06:24rany has joined #asahi-dev
06:26user has joined #asahi-dev
06:26user is now known as Guest15492
06:54hdbngr has joined #asahi-dev
07:03hdbngr has quit [Ping timeout: 480 seconds]
07:06hdbngr has joined #asahi-dev
07:10chadmed has quit [Quit: Konversation terminated!]
07:12___nick___ has joined #asahi-dev
07:15hdbngr has quit [Ping timeout: 480 seconds]
07:35eluks has quit [Remote host closed the connection]
07:35eluks has joined #asahi-dev
07:41chadmed has joined #asahi-dev
07:50hdbngr has joined #asahi-dev
07:58hdbngr has quit [Ping timeout: 480 seconds]
08:00RafayThe iperf3 speeds are very low and it breaks by the end of the test. I don't know why it's breaking at the end but speeds are around 10.5 Mbits/s which is quite low.
08:04RafayAlso aside from error 88: [ 63.138266] thunderbolt-apple-acio 501ac0000.nhi: RTKit: syslog message: high_speed_lane.c:289: Gen2/3 link error. lane=0, error=84
08:04Rafayhigh_speed_lane.c:289: Gen2/3 link error. lane=1, error=82
08:08Ariadne_ has quit [Read error: Connection reset by peer]
08:10hdbngr has joined #asahi-dev
08:11sventhat’s just the same thing essentially
08:11svenno idea why perf is so low, are you sure it’s going over tbt?
08:11sveneveryone has had issue getting it to actually use the thunderbolt0 interface so far
08:17Ariadne has joined #asahi-dev
08:17RafayI have no other interface, besides loopback and disconnected ethernet.
08:19Rafay[ 2862.192205] TCP: thunderbolt0: Driver has suspect GRO implementation, TCP performance may be compromised.
08:20Rafaysven: The above line is also in my dmesg quite late after the thunderbolt messages.
08:20hdbngr has quit [Ping timeout: 480 seconds]
08:23hdbngr has joined #asahi-dev
08:24chaos_princessare you using udp
08:24leiofwiw, the GRO message happens for end0 for 10G Aquantia AQtion AQC113 (Antigua 10G) as well, been idly wondering about that, but no speed issues there at 400 Mbps levels at least
08:26Rafaychaos_princess: UDP
08:27Rafaychaos_princess: sorry, I meant TCP.
08:36chadmedi suspect theres either something wrong with doing interchange on >2 surfaces, or kwin does weird things with the framebuffers that dcp does not like
08:37chadmedif mutter also explodes horribly then its probably the former
08:37chadmed(cc oliver)
08:37hdbngr has quit [Ping timeout: 480 seconds]
08:38hardy94 has quit [Quit: hardy94]
08:44chadmed has quit [Quit: Konversation terminated!]
08:46chadmed has joined #asahi-dev
08:46nano has quit [Quit: User left the chat]
08:47chadmedok turns out it was neither of those things, it was allowing all scanout buffers to use interchange. i guess we have to ensure that the buffer has a valid pixel format before we allow it or something
08:54chadmed has quit [Quit: Konversation terminated!]
08:59hardy94 has joined #asahi-dev
08:59kat[m] has joined #asahi-dev
09:00chadmed has joined #asahi-dev
09:06chadmedive updated mesa to do the right thing
09:07hdbngr has joined #asahi-dev
09:16hdbngr has quit [Ping timeout: 480 seconds]
09:25hdbngr has joined #asahi-dev
09:28chadmedkwin doesnt expose a linux-dmabuf tranche with dcp as the target
09:28chadmediirc mutter does
09:33hdbngr has quit [Ping timeout: 480 seconds]
09:37jannauI suspect this might be somewhat intentionally avoided in released kwin due to multi-gpu issues. might work kwin master after https://zamundaaa.github.io/wayland/2026/07/31/fixing-multi-gpu.html
09:37chadmedi just saw that too :D
09:37chadmedwell at least interchange works on all supported iosurfaces so im happy with that
09:39chadmedim pretty sure the kernel branch i linked should Just Work with ycc surfaces too but i've not got an easy way to test that
09:39chadmedgstreamer kmssink always uses linear framebuffers and mpv's drm vo can only output rgb
09:40chadmeddoes igt stress test modifiers?
09:41pb17 has quit [Ping timeout: 480 seconds]
09:42pb17 has joined #asahi-dev
09:43hdbngr has joined #asahi-dev
09:43jannauit certainly will not test unknown modifiers
09:44chadmedproblem for another day
09:45jannauI'm not sure the kernel driver will will work with (all) YCrCb formats out of te box. according to macos pixel format information those may uses a different tiling format
09:46chadmedhm, i thought it was just the luma tiles being bigger
09:47chadmedwe'll see, but worst case scenario we just limit those to linear. not sure we know how to get avd to spit out interchange anyway
09:57hdbngr has quit [Remote host closed the connection]
09:57hdbngr has joined #asahi-dev
10:36Rafaysven: Speeds from macos are around 1.8-2 Gbits/sec . I think it's because the other host is an older device with only thunderbolt 3 support (Intel Alpine Ridge 2c).
11:48sofuschadmed: i was stupid the last time i traced, im definitely seing a difference now
11:49chadmedoooh lets go
11:49sofusdifference being the fw writes 0 instead of output addresses
11:50chadmedinteresting
13:34___nick___ has quit []
13:36___nick___ has joined #asahi-dev
13:37___nick___ has quit []
13:40___nick___ has joined #asahi-dev
13:58myria has quit [Ping timeout: 480 seconds]
14:00tobhe has joined #asahi-dev
14:26nano has joined #asahi-dev
14:26Rafay has quit [Remote host closed the connection]
14:26Rafay_ is now known as Rafay
14:35hdbngr has quit [Ping timeout: 480 seconds]
15:04Yushi has quit [Remote host closed the connection]
15:05Yushi has joined #asahi-dev
15:11myria has joined #asahi-dev
15:40hdbngr has joined #asahi-dev
15:55hdbngr has quit [Ping timeout: 480 seconds]
16:00bgb has quit [Remote host closed the connection]
16:00bgb has joined #asahi-dev
16:01hdbngr has joined #asahi-dev
16:10yukahas anyone seen this? "ieee80211 phy0: brcmf_inform_bss: BSS info version 116 unsupported"
16:10yukatrying wifi with 26.6 fw
16:26hdbngr has quit [Ping timeout: 480 seconds]
16:29myria has quit [Ping timeout: 480 seconds]
16:35hdbngr has joined #asahi-dev
16:43rhysmdnz has quit [Quit: Bridge terminating on SIGTERM]
16:43Jamie1 has quit [Quit: Bridge terminating on SIGTERM]
16:50rhysmdnz has joined #asahi-dev
16:51Guest15533 has joined #asahi-dev
16:54hdbngr has quit [Ping timeout: 480 seconds]
16:55__nick__ has joined #asahi-dev
16:58___nick___ has quit [Ping timeout: 480 seconds]
17:01hdbngr has joined #asahi-dev
17:05floklinot in the last 6 months
17:10hdbngr has quit [Ping timeout: 480 seconds]
17:13myria has joined #asahi-dev
17:17hdbngr has joined #asahi-dev
17:21pb17 has quit [Ping timeout: 480 seconds]
17:24pb17 has joined #asahi-dev
17:26hdbngr has quit [Ping timeout: 480 seconds]
17:33hardy94 has quit [Quit: hardy94]
17:33hdbngr has joined #asahi-dev
17:42hdbngr has quit [Ping timeout: 480 seconds]
17:49hdbngr has joined #asahi-dev
17:58hdbngr has quit [Ping timeout: 480 seconds]
17:59hdbngr has joined #asahi-dev
18:09svenrafay: that’s still fairly slow, but at least m2 more or less works, so that’s good to know!
18:09svenNeed to fix the tipd issue and then figure out why the pro chips eat anything that’s sent on ring1 :/
18:10svenand then write dt-bindings and clean the rest up and then this should be ready for upstream submission
18:11svenand then it’s time to go back to the PCIe hotplug horrors
18:14hdbngr has quit [Ping timeout: 480 seconds]
18:19Rafaysven: Yeah. Btw, do you think this speed issue is unrelated to the tbt driver and maybe related to other stuff like the networking stack?
18:20svenno idea
18:20sveni think lane bonding is broken somehow but that’s at most a 2x speedup
18:21svenId blame the driver for now until proven otherwise
18:21chaos_princessthere was some questionable things in tb core, but thats probably due to "works on intel"
18:22hdbngr has joined #asahi-dev
18:22svenI really hope I won’t have to debug that core
18:23svenI already know more about how all that works than I’d like
18:37hdbngr has quit [Ping timeout: 480 seconds]
18:45hdbngr has joined #asahi-dev
18:54hdbngr has quit [Ping timeout: 480 seconds]
18:54Rafaysven: haha. By this time you probably have more info about tbt than anyone else.
18:55svenwhat still baffles me is that m1 works, M1 Pro doesn’t, and then m2 works again
18:58Rafaysven: Yeah, that's weird.
18:59svenand thanks to the tracer it’s also obvious it’s nothing else in the stack
18:59svenit writes stuff into ring1 but then no interrupt for that one ever fires
19:04hdbngr has joined #asahi-dev
19:10Rafaysven: No idea about that.
19:16hdbngr has quit [Ping timeout: 480 seconds]
19:17hdbngr has joined #asahi-dev
19:26yukaIs the irq num maybe wrong?
19:27hdbngr has quit [Ping timeout: 480 seconds]
19:28svenunlikely, the ring 0 irqs work and the ring 1 are right next to them
19:34hdbngr has joined #asahi-dev
19:44hdbngr has quit [Ping timeout: 480 seconds]
19:46hdbngr has joined #asahi-dev
19:55hdbngr has quit [Ping timeout: 480 seconds]
20:00aissen has quit [Ping timeout: 480 seconds]
20:02hdbngr has joined #asahi-dev
20:08bgb has quit [Remote host closed the connection]
20:08bgb has joined #asahi-dev
20:12hdbngr has quit [Ping timeout: 480 seconds]
20:20hdbngr has joined #asahi-dev
20:21nicolas17 has quit [Remote host closed the connection]
20:28Extern has quit [Quit: WeeChat 4.10.0]
20:29hdbngr has quit [Ping timeout: 480 seconds]
20:39hdbngr has joined #asahi-dev
20:42nicolas17 has joined #asahi-dev
20:44chadmed has quit [Quit: Konversation terminated!]
20:44chadmed has joined #asahi-dev
20:53hdbngr has quit [Remote host closed the connection]
20:53hdbngr has joined #asahi-dev
21:02hdbngr has quit [Ping timeout: 480 seconds]
21:06leah has quit [Quit: i will return]
21:08hdbngr has joined #asahi-dev
21:17hdbngr has quit [Ping timeout: 480 seconds]
21:20voidah has joined #asahi-dev
21:27hdbngr has joined #asahi-dev
21:28bgb has quit [Remote host closed the connection]
21:28bgb has joined #asahi-dev
21:34bgb has quit [Remote host closed the connection]
21:35bgb has joined #asahi-dev
21:40hdbngr has quit [Remote host closed the connection]
21:40hdbngr has joined #asahi-dev
21:46voidah has quit [Remote host closed the connection]
21:49voidah has joined #asahi-dev
22:00voidah has quit [Ping timeout: 480 seconds]
22:05hdbngr has quit [Ping timeout: 480 seconds]
22:10voidah has joined #asahi-dev
22:12revadam has joined #asahi-dev
22:13revadam has quit []
22:16hdbngr has joined #asahi-dev
22:20voidah has quit [Ping timeout: 480 seconds]
22:26hdbngr has quit [Ping timeout: 480 seconds]
22:27voidah has joined #asahi-dev
22:35hdbngr has joined #asahi-dev
22:36voidah has quit [Ping timeout: 480 seconds]
22:43hdbngr has quit [Ping timeout: 480 seconds]
22:46voidah has joined #asahi-dev
22:49hdbngr has joined #asahi-dev
22:54voidah has quit [Ping timeout: 480 seconds]
23:00hdbngr has quit [Ping timeout: 480 seconds]
23:03voidah has joined #asahi-dev
23:08hdbngr has joined #asahi-dev
23:11voidah has quit [Ping timeout: 480 seconds]
23:17hdbngr has quit [Ping timeout: 480 seconds]
23:19voidah has joined #asahi-dev
23:24leah has joined #asahi-dev
23:24hdbngr has joined #asahi-dev
23:28voidah has quit [Ping timeout: 480 seconds]
23:33hdbngr has quit [Ping timeout: 480 seconds]
23:35voidah has joined #asahi-dev
23:40hdbngr has joined #asahi-dev
23:44voidah has quit [Ping timeout: 480 seconds]
23:49hdbngr has quit [Ping timeout: 480 seconds]
23:52voidah has joined #asahi-dev
23:54nnym has quit [Remote host closed the connection]
23:54nnym has joined #asahi-dev
23:57hdbngr has joined #asahi-dev
…