Created attachment 116675 [details] Contents of /sys/class/drm/card0/error Since upgrading my Intel NUC5i5MYHE with the Core i5-5300U CPU from Linux kernel 4.0.5 to Linux kernel 4.1.0, I now get repeated GPU hangs about every 6 seconds starting immediately after boot. I have attached both the dmesg output showing the hang messages and the contents of /sys/class/drm/card0/error, as requested by the first hang message. This is a headless system and does not have Xorg installed or running (only the framebuffer console is active). The "monitor" attached is a dummy display simulator dongle attached to a Mini DisplayPort to HDMI connector and not a real monitor. Plugging in a real (DVI) monitor using another adapter yields the same hangs, as does plugging in no monitor at all. While the real monitor is attached, I can detect the GPU hangs as jerkiness in display updates, but the console is still usable.
Created attachment 116676 [details] output of lspci
Created attachment 116677 [details] output of dmesg
Try intel_iommu=igfx_off
I replaced the "intel_iommu=on" I had on the kernel command line with "intel_iommu=on,igfx_off" and now the hangs are gone. Thanks!
*** This bug has been marked as a duplicate of bug 89360 ***
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.