Hello, I just retry with more information : Before the bug : launch 1 of cat /proc/interrupts : 150: 0 12500 0 0 0 0 0 0 IR-PCI-MSI 327680-edge xhci_hcd 130: 0 0 36 0 0 0 0 0 IR-PCI-MSI 212992-edge xhci_hcd 195: 0 0 0 765 0 0 43917 0 IR-PCI-MSI 32768-edge i915
NMI: 3 3 2 3 1 1 2 1 Non-maskable interrupts LOC: 44084 45148 38917 43380 44347 39950 63891 41043 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 3 3 2 3 1 1 2 1 Performance monitoring interrupts IWI: 1983 1796 1016 1318 1958 1772 34849 1872 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 3202 2551 2333 2750 2945 2053 2450 1637 Rescheduling interrupts CAL: 32361 34041 33199 33443 32830 38261 30730 34866 Function call interrupts TLB: 4600 6819 7900 4979 5689 4671 7387 5792 TLB shootdowns TRM: 2 2 2 2 2 2 2 2 Thermal event interrupts launch 2 : 150: 0 15248 0 0 0 0 0 0 IR-PCI-MSI 327680-edge xhci_hcd 195: 0 0 0 765 0 0 71819 0 IR-PCI-MSI 32768-edge i915 130: 0 0 36 0 0 0 0 0 IR-PCI-MSI 212992-edge xhci_hcd LOC: 51305 53966 47267 51999 52140 47294 79287 48834 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 3 3 3 3 1 1 2 1 Performance monitoring interrupts IWI: 2723 2250 1249 1604 2447 2329 43610 2303 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 3317 2567 2347 2847 2984 2073 2462 1660 Rescheduling interrupts CAL: 33566 35684 34317 34273 33811 39276 32427 35700 Function call interrupts TLB: 4673 7130 7953 5017 5757 4764 7442 5869 TLB shootdowns TRM: 2 2 2 2 2 2 2 2 Thermal event interrupts I stress and the bug start ! launch 1 after the bug : 195: 7550 0 0 765 0 0 964697 0 IR-PCI-MSI 32768-edge i915 150: 7011 37888 0 0 0 0 0 10041 IR-PCI-MSI 327680-edge xhci_hcd 130: 10 0 36 0 0 0 0 9 IR-PCI-MSI 212992-edge xhci_hcd NMI: 4 6 6 4 1 1 4 3 Non-maskable interrupts LOC: 460124 453153 482067 473181 455918 460154 609368 463418 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 6 6 4 1 1 4 3 Performance monitoring interrupts IWI: 28098 23300 16538 19575 21421 22590 505527 24870 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 23455 16173 11638 19702 12745 12816 11421 15952 Rescheduling interrupts CAL: 131999 114719 106123 98885 108117 112193 110945 100299 Function call interrupts TLB: 28703 24931 27732 24161 29120 27679 33927 25081 TLB shootdowns TRM: 18027 18039 18034 18040 18039 18038 18027 18032 Thermal event interrupts Launch 2 after the bug : 195: 7550 0 0 765 0 0 975853 0 IR-PCI-MSI 32768-edge i915 150: 7011 37888 0 0 0 0 0 14097 IR-PCI-MSI 327680-edge xhci_hcd 130: 10 0 36 0 0 0 0 9 IR-PCI-MSI 212992-edge xhci_hcd NMI: 4 6 6 4 1 1 4 3 Non-maskable interrupts LOC: 475743 467326 495500 486893 469212 473011 627064 475719 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 6 6 4 1 1 4 3 Performance monitoring interrupts IWI: 28347 23568 16744 19857 21781 22822 509934 25016 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 23884 16483 11939 20083 13046 13066 11795 16264 Rescheduling interrupts CAL: 134980 116528 107930 100950 109829 113764 112513 102450 Function call interrupts TLB: 28963 25337 28244 24965 29848 28542 34381 26287 TLB shootdowns TRM: 18027 18039 18034 18040 18039 18038 18027 18032 Thermal event interrupts I took computer in sleep (to ram). Launch 1 after sleep to ram : 130: 27 0 36 0 0 0 0 9 IR-PCI-MSI 212992-edge xhci_hcd 150: 13903 37888 0 0 0 0 0 26119 IR-PCI-MSI 327680-edge xhci_hcd 195: 11261 0 0 765 0 0 1003825 0 IR-PCI-MSI 32768-edge i915 NMI: 4 7 6 4 1 1 4 3 Non-maskable interrupts LOC: 519129 504372 527153 522688 499834 505420 672580 507475 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 7 6 4 1 1 4 3 Performance monitoring interrupts IWI: 30347 24518 17476 20953 22471 23544 520858 25509 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 24172 16752 12247 20356 13343 13283 12083 16471 Rescheduling interrupts CAL: 142469 120015 110136 102602 111750 115151 114492 104340 Function call interrupts TLB: 29489 25547 28486 25180 30499 28753 34731 26790 TLB shootdowns TRM: 18329 18341 18336 18342 18341 18340 18329 18334 Thermal event interrupts Launch 2 after sleep to ram : 130: 27 0 36 0 0 0 0 9 IR-PCI-MSI 212992-edge xhci_hcd 150: 16466 37888 0 0 0 0 0 26119 IR-PCI-MSI 327680-edge xhci_hcd 195: 19428 0 0 765 0 0 1003825 0 IR-PCI-MSI 32768-edge i915 NMI: 4 7 6 4 1 1 4 3 Non-maskable interrupts LOC: 526158 508337 531159 525993 502553 508013 675668 510132 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 7 6 4 1 1 4 3 Performance monitoring interrupts IWI: 33520 24645 17938 21132 22777 23691 521025 25655 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 24191 16765 12258 20371 13359 13290 12096 16482 Rescheduling interrupts CAL: 143047 120257 110382 102735 111925 115295 114611 104471 Function call interrupts TLB: 29512 25560 28512 25199 30508 28764 34740 26805 TLB shootdowns TRM: 18593 18605 18600 18606 18605 18604 18593 18598 Thermal event interrupts I put the computer in hibernate mode (suspend to disk) with a hardware power off : Launch 1 after hibernate : 130: 0 0 0 0 28 0 0 0 IR-PCI-MSI 212992-edge xhci_hcd 170: 0 0 16 0 0 7256 0 0 IR-PCI-MSI 327680-edge xhci_hcd 195: 28237 0 0 765 0 0 1005308 0 IR-PCI-MSI 32768-edge i915 NMI: 4 7 6 4 1 1 4 3 Non-maskable interrupts LOC: 535269 514963 536431 532550 507381 513912 681769 516132 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 7 6 4 1 1 4 3 Performance monitoring interrupts IWI: 37082 24906 18146 21769 22908 23786 521750 26106 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 24265 16910 12322 20523 13505 13349 12203 16521 Rescheduling interrupts CAL: 144085 120849 110834 103135 112402 115806 115137 104920 Function call interrupts TLB: 29596 25732 28569 25252 30694 28988 34829 26910 TLB shootdowns TRM: 19114 19108 19121 19127 19126 19103 19114 19119 Thermal event interrupts Launch 2 after hibernate : 130: 0 0 0 0 28 0 0 0 IR-PCI-MSI 212992-edge xhci_hcd 170: 0 0 2134 0 0 7256 0 0 IR-PCI-MSI 327680-edge xhci_hcd 195: 28237 0 0 765 0 0 1012675 0 IR-PCI-MSI 32768-edge i915 NMI: 4 7 6 4 1 1 4 3 Non-maskable interrupts LOC: 538751 519114 539354 535473 510776 516881 687635 519530 Local timer interrupts SPU: 1 0 0 0 0 0 0 0 Spurious interrupts PMI: 4 7 6 4 1 1 4 3 Performance monitoring interrupts IWI: 37494 25114 18205 21923 23274 23934 524635 26330 IRQ work interrupts RTR: 0 0 0 0 0 0 0 0 APIC ICR read retries RES: 24271 16917 12330 20540 13519 13361 12209 16528 Rescheduling interrupts CAL: 144586 121170 111031 103286 112578 115952 115405 105096 Function call interrupts TLB: 29623 25742 28579 25278 30708 29004 34852 26937 TLB shootdowns TRM: 19510 19504 19517 19523 19522 19499 19510 19515 Thermal event interrupts Interrupt continue to be present but Xorg use lot of CPU and system is usable. Anyone have an idea ? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2007853 Title: Intel video driver i915 - Repeated GPU HANG's - Xorg use a lot of CPU Status in linux package in Ubuntu: Confirmed Bug description: Hello, I think my problem is link to firmware package or make hardware error. Lot of people have problem with the i915. I have take lot of time to configure it correctly. Today my configuration is ok with 5.19.0-32-generic, it seem the same with 5.15.0-60. I'm on Ubuntu 22.04 LTS ("The Jammy Jellyfish") I'm not sure when the problem have really started, but I propose you to firstly see the problem in the global way. I'm not sure It wan really depend on a kernel or a configuration. My BIOS is up to date and all the system . So today my i915 integrated card work well with my 11th Gen Intel® Core™ i5. I have configure it, all drivers seem to be ok. VMWare work with accelerate 3D graphics, VLC work with OpenGL Output and hardware VDPAU or VD-API. Mesa seem to be ok, Firefox work with hardware video acceleration. glmark2 and glxgears is ok to. Xorg use very few CPU. ALT+TAB is very speed to change between applications. TAB changing on Firefox is very speed to. Videos are fluid and use few CPU. Intel_GPU_top show that vlc use hardware. But at an aleatory time or with using a lot of CPU/GPU a problem arrive ! My test process is VLC with a 1080p movie with a good encoding 5Go for an 1 hours. Firefox with a 720p or 1080 video on YouTube in incrustation VMWare with a Windows XP VM testing Dxdiag. The 3 is visible partially at the same time on my screen. I'm launching the 3, and I launch dxdiag video test on the VM. When It arrive to Direct 3D 7 or 8 or 9 the problem start. Before this, all is ok, fluid. (DXDiag 7, 8 or 9 are never are fluid, but I'm not sure VMWare work well with this old version) I think it normal at a moment to saturate the CPU or GPU, here it seem to be the case, the YouTube video and vlc video skip frame and freeze and jerk. But when the test is finish, it will go back at a normally state few time after, I think. Now the system is not fluid, ALT+TAB lag, jerk, changing tab on firefox it very long, system monitor is very long. All graphical software is very long. Video are not fluid. Xorg start taking a lot of CPU even if nothing is done. If I suspend system and resume it, it is better but not fluid. If I hibernate (suspend to disk) with an hardware reset it is very fluid. Sometime it seem to be totally normal. Before do anything I see with cat /proc/interrupts a lot of interrupts on IR-PCI-MSI 327680-edge xhci_hcd. For example : 325180. After an hibernation I have "only" 102178 for xhci_hcd. When I restart before any suspend, I can have the bios screen very long to appear and the grub menu not fluid, very slow. I thinks I'm keep the bug some time after reset. On forum people deal with lost of video sync. I think it can be anything that. With a power off it work normally, so the hardware reset have an impact. In dmesg I only have : (when the problem start) [ 5546.086667] x86/split lock detection: #AC: main-svga/14494 took a split_lock trap at address: 0x559ce0ea2e3d [ 5546.291794] x86/split lock detection: #AC: vmx-svga/14491 took a split_lock trap at address: 0x563fc34febb7 [ 5546.310412] x86/split lock detection: #AC: main-mks/14493 took a split_lock trap at address: 0x559ce0ea30a7 nothing else. VLC have this error : [h264 @ 0x7fa854c9e300] get_buffer() failed [h264 @ 0x7fa854c9e300] thread_get_buffer() failed [h264 @ 0x7fa854c9e300] decode_slice_header error [h264 @ 0x7fa854c9e300] no frame! [h264 @ 0x7fa854d8f3c0] get_buffer() failed [h264 @ 0x7fa854d8f3c0] thread_get_buffer() failed [h264 @ 0x7fa854d8f3c0] decode_slice_header error [h264 @ 0x7fa854d8f3c0] no frame! [00005560d6746a70] vlcpulse audio output error: digital pass-through stream connection failure: Non pris en charge [00005560d6746a70] main audio output error: module not functional [00007fa854cebd50] main decoder error: failed to create audio output [00005560d6746a70] vlcpulse audio output error: digital pass-through stream connection failure: Non pris en charge [00005560d6746a70] main audio output error: module not functional [00007fa854cebd50] main decoder error: failed to create audio output [00005560d6746a70] main audio output error: cannot add user visualization "any" (skipped) [00007fa854c19430] avcodec decoder: Using Intel iHD driver for Intel(R) Gen Graphics - 22.3.1 () for hardware decoding I can see it on syslog nothing else. Nothing in xorg log. It surprising me to keep the problem in grub menu so I think is more an hardware problem triggered or a driver error. Anyone have an idea of what it could be ? Thanks in advance Have a good day. David To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2007853/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
