Overview: The display is distorted when power-profile low or mid is activated. Steps to reproduce: echo low > /sys/class/drm/card0/device/power_profile or echo mid > /sys/class/drm/card0/device/power_profile Actual Results: The display is distorted, but the system is still usable. The distortion consists of noisy flickering vertical stripes, with columns between them that look ok. When I choose powerprofile default or auto or high the distortion goes away and everything's as before. Output of cat /sys/kernel/debug/dri/{0,64}/radeon_pm_info: With powerprofile default: default engine clock: 500000 kHz current engine clock: 499500 kHz default memory clock: 600000 kHz current memory clock: 594000 kHz voltage: 1000 mV PCIE lanes: 16 default engine clock: 500000 kHz current engine clock: 499500 kHz default memory clock: 600000 kHz current memory clock: 594000 kHz voltage: 1000 mV PCIE lanes: 16 With powerprofile mid: default engine clock: 500000 kHz current engine clock: 124870 kHz default memory clock: 600000 kHz current memory clock: 405000 kHz voltage: 900 mV PCIE lanes: 16 default engine clock: 500000 kHz current engine clock: 124870 kHz default memory clock: 600000 kHz current memory clock: 405000 kHz voltage: 900 mV PCIE lanes: 16 With powerprofile low: default engine clock: 500000 kHz current engine clock: 124870 kHz default memory clock: 600000 kHz current memory clock: 405000 kHz voltage: 900 mV PCIE lanes: 16 default engine clock: 500000 kHz current engine clock: 124870 kHz default memory clock: 600000 kHz current memory clock: 405000 kHz voltage: 900 mV PCIE lanes: 16 With powerprofile high: default engine clock: 500000 kHz current engine clock: 499500 kHz default memory clock: 600000 kHz current memory clock: 594000 kHz voltage: 1000 mV PCIE lanes: 16 default engine clock: 500000 kHz current engine clock: 499500 kHz default memory clock: 600000 kHz current memory clock: 594000 kHz voltage: 1000 mV PCIE lanes: 16 Expected Results: No display distortion and perhaps other values in radeon_pm_info (values of mid and low profile should differ and perhaps there should have been some lanes deactivated by these profiles). Btw. there is no such problem when I use the powermanagement-features in xorg.conf (ForceLowPowerMode, ClockGating, DynamicPM) without KMS enabled. Versions: See attached logfiles. Bug exists since power-profiles had been introduced (in kernel 2.6.34 or 2.6.35).
Created attachment 47447 [details] Logfile of Xorg Also attached Xorg.0.log.
Created attachment 47448 [details] Output of dmesg Also attached output of dmesg.
-- GitLab Migration Automatic Message -- This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity. You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/drm/amd/issues/193.
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.