Bug 1000160
| Summary: | AMD UVD driver is unstable in kernel 3.10 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Product: | [Fedora] Fedora | Reporter: | Václav Mocek <next.little.owl> | ||||||||
| Component: | xorg-x11-drv-ati | Assignee: | X/OpenGL Maintenance List <xgl-maint> | ||||||||
| Status: | CLOSED WORKSFORME | QA Contact: | Fedora Extras Quality Assurance <extras-qa> | ||||||||
| Severity: | high | Docs Contact: | |||||||||
| Priority: | unspecified | ||||||||||
| Version: | 19 | CC: | gansalmon, itamar, jonathan, kernel-maint, madhu.chinakonda, marcelo.barbosa, xgl-maint | ||||||||
| Target Milestone: | --- | ||||||||||
| Target Release: | --- | ||||||||||
| Hardware: | Unspecified | ||||||||||
| OS: | Unspecified | ||||||||||
| Whiteboard: | |||||||||||
| Fixed In Version: | Doc Type: | Bug Fix | |||||||||
| Doc Text: | Story Points: | --- | |||||||||
| Clone Of: | Environment: | ||||||||||
| Last Closed: | 2014-02-02 15:13:50 UTC | Type: | Bug | ||||||||
| Regression: | --- | Mount Type: | --- | ||||||||
| Documentation: | --- | CRM: | |||||||||
| Verified Versions: | Category: | --- | |||||||||
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |||||||||
| Cloudforms Team: | --- | Target Upstream Version: | |||||||||
| Embargoed: | |||||||||||
| Attachments: |
|
||||||||||
Created attachment 789347 [details]
dmesg log
Created attachment 789348 [details]
Xorg log
I can confirm that problem was fixed in the newer version of xorg-x11-drv-ati (tested on APU Trinity/Richland) and I suggest to close this bug as fixed. |
Created attachment 789346 [details] Information extracted from systemd journal. Description of problem: When a video player uses UVD in AMD APU to accelerate video decoding (a new feature in kernel 3.10), the GPU sooner or later stalls. Version-Release number of selected component (if applicable): $ uname -a Linux amulet 3.10.7-200.fc19.x86_64 #1 SMP Thu Aug 15 23:19:45 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux $rpm -qa | grep mesa mesa-libgbm-9.2-0.14.20130723.fc19.x86_64 mesa-dri-drivers-9.2-0.14.20130723.fc19.x86_64 mesa-filesystem-9.2-0.14.20130723.fc19.x86_64 mesa-libxatracker-9.2-0.14.20130723.fc19.x86_64 mesa-libglapi-9.2-0.14.20130723.fc19.x86_64 mesa-libEGL-9.2-0.14.20130723.fc19.x86_64 mesa-libwayland-egl-9.2-0.14.20130723.fc19.x86_64 mesa-libGL-9.2-0.14.20130723.fc19.x86_64 How reproducible: Always. Play a DivX MPEG-4 video using Totem and you have a higher change winning a lottery than watching a two hours film without reset. Actual results: GPU stalls and the PC monitor indicates that there is no input. Sometimes the system recovers (a successful GPU reset, very rare), sometimes it continues running without a video output, sometime it resets itself. Confirmed on two PC with A6-5400K and A10-5800K. Additional info: A few hints from the systemd journal: Aug 21 21:41:24 amulet kernel: radeon 0000:00:01.0: GPU fault detected: 146 0x02a67104 Aug 21 21:41:25 amulet kernel: radeon 0000:00:01.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0000092A Aug 21 21:41:25 amulet kernel: radeon 0000:00:01.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x06071004 ... Aug 21 21:41:35 amulet kernel: radeon 0000:00:01.0: GPU lockup CP stall for more than 10000msec Aug 21 21:41:35 amulet kernel: radeon 0000:00:01.0: GPU lockup (waiting for 0x0000000000075e5d last fence id 0x0000000000075e ... Aug 21 21:41:35 amulet kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=00:01.0 domain=0x0003 address=0x000000003017b340 fl Aug 21 21:41:35 amulet kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=00:01.0 domain=0x0003 address=0x000000003017b340 fl ... Aug 21 21:41:35 amulet kernel: radeon 0000:00:01.0: GPU softreset: 0x0000000D ... Aug 22 20:16:46 amulet kernel: radeon 0000:00:01.0: GPU reset succeeded, trying to resume