#asahi-dev · 2026-08-19 18:23
jannauisn't that just "iommu.strict" config symbol or command line option?#asahi-dev · 2026-08-19 18:19
sveni think all we need to do it set some bit in capabilities somewhere since all we can do is "invalidate everything" anyway#asahi-dev · 2026-08-19 18:19
sveni guess we should add support for dma-fq to dart anyway#asahi-dev · 2026-08-19 18:16
jannauDMA-FQ helps now more. 13.2 Gbits/sec for Linux as receiver in perf3#asahi-dev · 2026-08-19 18:09
svenat least for the cpu pagetables you don't need to invalidate anything after adding new mappings, only when deleting old ones#asahi-dev · 2026-08-19 18:09
svennice!#asahi-dev · 2026-08-19 18:08
jannaucommenting apple_dart_domain_flush_tlb in apple_dart_iotlb_sync_map increases usb4net througput by 30%#asahi-dev · 2026-08-19 17:01
svenbut in theory datastatus/status should come from that EUDO message so this should hopefully be fine#asahi-dev · 2026-08-19 17:01
svenxnu takes it directly from datastatus/status but i can't pass those through to anything outside tipd#asahi-dev · 2026-08-19 16:59
chaos_princesssure, will do later today#asahi-dev · 2026-08-19 16:58
svenchaos_princess: if you have some time, can you try with your cables again as well? i've completely rewritten the cable vse nonsense and it should match whatever xnu does now#asahi-dev · 2026-08-19 16:51
sven"good"#asahi-dev · 2026-08-19 16:35
jannauwe're hitting the same issues in asahi-wip so unrelated#asahi-dev · 2026-08-19 16:16
sveni'm not too concerned if it works because pipehandler is just weird, but i thought we got rid of most of these warnings by now#asahi-dev · 2026-08-19 16:15
svenodd#asahi-dev · 2026-08-19 16:15
jannautiming wise the WARN_ON_ONCE() appears to be on the newly connected port (tbt disconnect, usb3 connect)#asahi-dev · 2026-08-19 16:13
svenmaybe we don't need the lock dance on disconnect? we're about to reset the entire thing anyway#asahi-dev · 2026-08-19 16:13
svenyeah, i hit that as well#asahi-dev · 2026-08-19 16:12
jannauthe "phy-apple-atc f03000000.phy: Pipehandler lock not acked" was from the usb3 disconenct of a different port#asahi-dev · 2026-08-19 16:11
jannaudevices works though#asahi-dev · 2026-08-19 16:11
svenhm, i see that on tbt disconnect here#asahi-dev · 2026-08-19 16:11
jannaustill hits "phy-apple-atc f03000000.phy: Pipehandler lock not acked" and WARN_ON_ONCE(atcphy->pipehandler_up); in atcphy_mux_set() on usb3 connect#asahi-dev · 2026-08-19 16:08
svenbut either, happy it's fixed :D#asahi-dev · 2026-08-19 16:08
sventhey shouldn't affect xdomain connections I think#asahi-dev · 2026-08-19 16:07
svenwhat they were supposed to fix was tbt devices preventing acio shutdown#asahi-dev · 2026-08-19 16:07
svenmaybe they fixed that by accident#asahi-dev · 2026-08-19 16:06
jannausven: usb3 works now after tbt. I thought your thunderbolt fixes were supposed to fix it#asahi-dev · 2026-08-19 16:02
svenjannau: did you mention that usb3 devices after a tbt connection don't work anymore? i can't seem to reproduce that#asahi-dev · 2026-08-19 15:00
jannauworks on m2 pro#asahi-dev · 2026-08-19 14:55
sven*now#asahi-dev · 2026-08-19 14:55
svenexcept for dt-bindings i'm mostly happy with that branch nw#asahi-dev · 2026-08-19 14:55
sven*\o/#asahi-dev · 2026-08-19 14:55
sven\o.#asahi-dev · 2026-08-19 14:55
jannauseries sent#asahi-dev · 2026-08-19 14:54
svenack, pushed again with the new version#asahi-dev · 2026-08-19 14:54
jannau"||" vs. "&&" mixup in "if (args->args_count != 1 && args->args_count != 5)"#asahi-dev · 2026-08-19 14:53
jannauyes, nothing catastrophic just a "#asahi-dev · 2026-08-19 14:52
svenugh, okay. just the iommu series commits?#asahi-dev · 2026-08-19 14:47
jannautoo#asahi-dev · 2026-08-19 14:47
jannautwo early. old version contains a severe bug, fix pushed#asahi-dev · 2026-08-19 14:36
svengithub.com/AsahiLinux/linux/tree/tbt-reset-wip compile tested only, merged janne's commits so that this should work on m2 pro/... now as well#asahi-dev · 2026-08-19 14:29
sven„mostly“? :D#asahi-dev · 2026-08-19 14:17
jannau(mostly) everything still works after replacing "apple,dma-range"#asahi-dev · 2026-08-19 13:47
sofusthat looks right, im also seing the CompressionMetadataPatternSignallingConstant in the metadata#asahi-dev · 2026-08-19 13:34
jannaunv12 tiled/compressed should be https://paste.debian.net/hidden/7c6479fe#asahi-dev · 2026-08-19 13:19
sofusi find it kinda annoying that i have to add a new pixel format just to describe "this format but compressed"#asahi-dev · 2026-08-19 13:15
sofusim not sure, i have not been able to test it yet#asahi-dev · 2026-08-19 13:13
chadmedmaybe the dcp driver is wrong for yuv too then#asahi-dev · 2026-08-19 13:12
sofusyes, its only the metadata thats not the same as the dcp driver