Bug 94877

Summary: Radeon 7500: GPU lockup after starting Xorg
Product: xorg Reporter: macro
Component: Driver/RadeonAssignee: xf86-video-ati maintainers <xorg-driver-ati>
Status: RESOLVED MOVED QA Contact: Xorg Project Team <xorg-team>
Severity: critical    
Priority: medium CC: julien.isorce
Version: 7.7 (2012.06)   
Hardware: PowerPC   
OS: Linux (All)   
Whiteboard:
i915 platform: i915 features:
Attachments:
Description Flags
Full dmesg
none
Full Xorg.0.log
none
Full dmesg (radeon.agpmode=-1)
none
Full Xorg.0.log (radeon.agpmode=-1) none

Description macro 2016-04-09 12:48:12 UTC
After starting Xorg, interaction with the gui quickly causes the GPU to lock up with "ring 0 stalled for more than 10000msec" kernel messages.

Almost any GUI interaction triggers the lockup.  It's just a question of how long it takes, with interaction involving "more painting" triggering it faster.

The lockup does not occur as long as there is no gui interaction.  Just moving the mouse around does not trigger it.

This of course makes Xorg unusable on this system.

The Linux+Xorg stack did work reliably on this machine until early 2010, with reasonable 2D and 3D performance (for the hardware).  I did not use it between then and 2015, when I reinstalled an up-to-date version of Linux and Xorg stopped working.

The machine is, from uname -a, Gentoo "Linux 4.5.0-gentoo-r1" running on a "ppc 7400, altivec supported PowerMac5,1".

The video card is, from Xorg.0.log, an "ATI Radeon 7500 QW (AGP/PCI) (ChipID = 0x5157)".

Dmesg and Xorg.0.log attached.

Following are a few detailed examples of interactions triggering the lockup, with the resulting kernel error messages.

I am happy to follow instructions to provide more information.  I can probably also arrange SSH access to the machine.
Comment 1 macro 2016-04-09 12:50:02 UTC
Created attachment 122834 [details]
Full dmesg
Comment 2 macro 2016-04-09 12:50:29 UTC
Created attachment 122835 [details]
Full Xorg.0.log
Comment 3 macro 2016-04-09 12:53:46 UTC
Example 1: Drag a window

(start xorg)
(open a window and drag it, contents displayed while dragging)
(window drags a few centimeters, but very slowly)
(screen freezes, contents still shown)
Apr 09 18:23:04 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10000msec
Apr 09 18:23:04 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000100 on ring 0)
Apr 09 18:23:05 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:05 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: Saved 27 dwords of commands on ring 0.
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8006C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C139
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:23:07 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:23:07 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:07 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:07 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:23:07 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:23:18 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10492msec
Apr 09 18:23:18 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000101 on ring 0)
Apr 09 18:23:18 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:23:18 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:23:18 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:18 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: Saved 254043 dwords of commands on ring 0.
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C135
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:23:20 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:23:20 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:20 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:20 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:23:20 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:23:31 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:23:31 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000102 on ring 0)
Apr 09 18:23:31 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:23:31 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:23:31 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:31 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:31 [kernel] radeon 0000:00:10.0: Saved 245915 dwords of commands on ring 0.
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C131
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:23:33 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:23:33 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:33 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:33 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:23:34 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:23:44 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10488msec
Apr 09 18:23:44 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000103 on ring 0)
Apr 09 18:23:44 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:23:44 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:23:44 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:44 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:44 [kernel] radeon 0000:00:10.0: Saved 237787 dwords of commands on ring 0.
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C12D
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:23:47 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:23:47 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:47 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:23:47 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:23:47 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:23:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10496msec
Apr 09 18:23:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000104 on ring 0)
Apr 09 18:23:57 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:23:57 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:23:57 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:23:57 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: Saved 229659 dwords of commands on ring 0.
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C129
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:24:00 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:24:00 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:00 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:00 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:24:00 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:24:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10360msec
Apr 09 18:24:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000105 on ring 0)
Apr 09 18:24:11 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:24:11 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:24:11 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:11 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: Saved 221531 dwords of commands on ring 0.
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C125
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:24:13 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:24:13 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:13 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:13 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:24:13 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:24:24 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:24:24 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000106 on ring 0)
Apr 09 18:24:24 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:24:24 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:24:24 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:24 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: Saved 213403 dwords of commands on ring 0.
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C121
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:24:26 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:24:26 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:26 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:26 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:24:26 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:24:37 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10476msec
Apr 09 18:24:37 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000107 on ring 0)
Apr 09 18:24:37 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:24:37 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:24:37 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:37 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: Saved 205275 dwords of commands on ring 0.
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C11D
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:24:39 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:24:39 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:39 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:39 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:24:39 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:24:50 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10488msec
Apr 09 18:24:50 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000108 on ring 0)
Apr 09 18:24:50 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:24:50 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:24:50 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:50 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: Saved 197147 dwords of commands on ring 0.
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C119
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:24:52 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:24:52 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:24:52 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:24:52 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:24:52 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:25:03 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:25:03 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x0000000000000109 on ring 0)
Apr 09 18:25:03 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:25:03 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:25:03 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:03 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:03 [kernel] radeon 0000:00:10.0: Saved 189019 dwords of commands on ring 0.
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C115
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:25:06 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:25:06 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:06 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:06 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:25:06 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:25:16 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10488msec
Apr 09 18:25:16 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x000000000000010a on ring 0)
Apr 09 18:25:16 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:25:16 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:25:16 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:16 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: Saved 180891 dwords of commands on ring 0.
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C111
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:25:19 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:25:19 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:19 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:19 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:25:19 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:25:29 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:25:29 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x000000000000010b on ring 0)
Apr 09 18:25:29 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:25:29 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:25:29 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:29 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: Saved 172763 dwords of commands on ring 0.
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C10D
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:25:32 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:25:32 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:32 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:32 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:25:32 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:25:43 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10488msec
Apr 09 18:25:43 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x000000000000010c on ring 0)
Apr 09 18:25:43 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:25:43 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:25:43 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:43 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: Saved 164635 dwords of commands on ring 0.
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C109
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:25:45 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:25:45 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:45 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:45 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:25:45 [kernel] [drm] ring test succeeded in 0 usecs
Apr 09 18:25:56 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:25:56 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x000000000000010d on ring 0)
Apr 09 18:25:56 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:25:56 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:25:56 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:56 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: Saved 156507 dwords of commands on ring 0.
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2570) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2591) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: (r100_asic_reset:2599) RBBM_STATUS=0x8002C105
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: GPU reset succeed
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: WB disabled
Apr 09 18:25:58 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xf106b000
Apr 09 18:25:58 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:25:58 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:25:58 [kernel] [drm] radeon: ring at 0x0000000000001000
Apr 09 18:25:58 [kernel] [drm] ring test succeeded in 0 usecs
(screen flashes black for 1-2 seconds, then redisplays contents from the time it froze)
Apr 09 18:26:09 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10484msec
Apr 09 18:26:09 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000000ff last fence id 0x000000000000010e on ring 0)
Apr 09 18:26:09 [kernel] [drm:r100_ib_test] *ERROR* radeon: fence wait failed (-35).
Apr 09 18:26:09 [kernel] [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on GFX ring (-35).
Apr 09 18:26:09 [kernel] radeon: wait for empty RBBM fifo failed ! Bad things might happen.
Apr 09 18:26:09 [kernel] Failed to wait GUI idle while programming pipes. Bad things might happen.
Apr 09 18:26:11 [kernel] radeon 0000:00:10.0: Saved 148379 dwords of commands on ring 0.
(machine becomes completely unresponsive, SSH sessions die, power cycle required, contents from the time it froze still displayed on screen)
Comment 4 macro 2016-04-09 12:54:47 UTC
Example 2: Desktop selection box

(start xorg)
(Click-drag on desktop, creating a shaded selection box)
(screen goes black)
Apr 09 18:06:15 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10000msec
Apr 09 18:06:15 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000000016 last fence id 0x0000000000000017 on ring 0)
(previous two lines repeat forever, screen stays black, machine stays accessible over SSH)
Comment 5 macro 2016-04-09 12:56:35 UTC
Example 3: Popup menus

(start xorg)
(repeatedly open and close root right-click menu for 20-30 seconds)
(screen goes black)
Apr 09 18:19:10 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10212msec
Apr 09 18:19:10 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x00000000000003e2 last fence id 0x00000000000003e4 on ring 0)
(previous two lines repeat forever, screen stays black, machine stays accessible over SSH)
Comment 6 Alex Deucher 2016-04-09 22:14:15 UTC
AGP is pretty problematic on Macs.  Does disabling AGP (append radeon.agpmode=-1 to your kernel command line) help?
Comment 7 macro 2016-04-10 00:08:22 UTC
Created attachment 122841 [details]
Full dmesg (radeon.agpmode=-1)
Comment 8 macro 2016-04-10 00:10:00 UTC
Created attachment 122842 [details]
Full Xorg.0.log (radeon.agpmode=-1)
Comment 9 macro 2016-04-10 05:09:17 UTC
Hi Alex,

Disabling AGP (see attached dmesg and Xorg.0.log) improves the situation somewhat.

The system seems to survive more gui interaction now, but still fails consistently before long.  Examples below.

Prior to failing, screen updates seem accurate (in that there are no painting glitches) but are disappointingly slow.  To be expected in PCI mode?

Thank you for your assistance, Alex.  I realise this obsolete hardware is probably of little interest to you (or AMD), but it's a collectors' item to me and means a lot so I really appreciate it.
Comment 10 macro 2016-04-10 05:11:28 UTC
(start xorg)
(open window with a scrollbar-scrollable region e.g. web browser)
(start scrolling using scrollbar)
(viewport scrolls a centimeter or two)
(screen freezes)
(exception information appears in Xorg.0.log, see "Full Xorg.0.log (radeon.agpmode=-1)" attachment)
(the folowing kernel messages appear)
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10000msec
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002424 last fence id 0x0000000000002425 on ring 0)
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: Saved 27 dwords of commands on ring 0.
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 09:53:57 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 09:53:57 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 09:53:57 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 09:53:57 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 09:53:57 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
(previous block of error messages repeats every 1-2 seconds forever, each time screen flashes black then redisplays frozen screen contents, machine stays responsive over SSH)
Comment 11 macro 2016-04-10 05:43:26 UTC
In this example, I discovered that moving the mouse triggers the "Saved ... dwords of commands" sequence, which otherwise occurrs every 30 seconds or so:


(start xorg)
(open a window e.g. terminal and maximise it)
(open another window e.g. file manager and drag it around in front of the maximised window for a few seconds)
(screen freezes with "tracers" of the last few frames of the moving window visible)
(exception information appears in Xorg.0.log similar to "Full Xorg.0.log (radeon.agpmode=-1)" attachment)
(the following kernel messages start appearing)
Apr 10 15:35:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10000msec
Apr 10 15:35:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:12 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10500msec
Apr 10 15:35:12 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:12 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11000msec
Apr 10 15:35:12 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:13 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11500msec
Apr 10 15:35:13 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:13 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12000msec
Apr 10 15:35:13 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:14 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12500msec
Apr 10 15:35:14 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:14 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13000msec
Apr 10 15:35:14 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:15 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13500msec
Apr 10 15:35:15 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:15 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14000msec
Apr 10 15:35:15 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:16 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14500msec
Apr 10 15:35:16 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:16 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15000msec
Apr 10 15:35:16 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:17 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15500msec
Apr 10 15:35:17 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:17 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16000msec
Apr 10 15:35:17 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:18 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16500msec
Apr 10 15:35:18 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:18 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17000msec
Apr 10 15:35:18 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:19 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17500msec
Apr 10 15:35:19 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:19 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18000msec
Apr 10 15:35:19 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:20 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18500msec
Apr 10 15:35:20 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:20 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19000msec
Apr 10 15:35:20 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:21 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19500msec
Apr 10 15:35:21 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:21 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20000msec
Apr 10 15:35:21 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:22 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20500msec
Apr 10 15:35:22 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:22 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21000msec
Apr 10 15:35:22 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:23 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21500msec
Apr 10 15:35:23 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:23 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 22000msec
Apr 10 15:35:23 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:35:24 [kernel] radeon 0000:00:10.0: Saved 59 dwords of commands on ring 0.
Apr 10 15:35:24 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:35:24 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:35:24 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:35:24 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:35:24 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:35:24 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:35:24 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:35:24 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:35:34 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10272msec
Apr 10 15:35:34 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:34 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10772msec
Apr 10 15:35:34 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:35 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11272msec
Apr 10 15:35:35 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:35 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11772msec
Apr 10 15:35:35 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:35:36 [kernel] radeon 0000:00:10.0: Saved 211419 dwords of commands on ring 0.
Apr 10 15:35:36 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:35:36 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:35:36 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:35:36 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:35:36 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:35:36 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:35:36 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:35:36 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:35:46 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10288msec
Apr 10 15:35:46 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:46 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10788msec
Apr 10 15:35:46 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:47 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11288msec
Apr 10 15:35:47 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:47 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11788msec
Apr 10 15:35:47 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:48 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12288msec
Apr 10 15:35:48 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:48 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12788msec
Apr 10 15:35:48 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:49 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13288msec
Apr 10 15:35:49 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:49 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13788msec
Apr 10 15:35:49 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:50 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14288msec
Apr 10 15:35:50 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:50 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14788msec
Apr 10 15:35:50 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:51 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15288msec
Apr 10 15:35:51 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:51 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15788msec
Apr 10 15:35:51 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:52 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16288msec
Apr 10 15:35:52 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:52 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16788msec
Apr 10 15:35:52 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:53 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17288msec
Apr 10 15:35:53 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:53 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17788msec
Apr 10 15:35:53 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:54 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18288msec
Apr 10 15:35:54 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:54 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18788msec
Apr 10 15:35:54 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:55 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19288msec
Apr 10 15:35:55 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:55 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19788msec
Apr 10 15:35:55 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:56 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20288msec
Apr 10 15:35:56 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:56 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20788msec
Apr 10 15:35:56 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21288msec
Apr 10 15:35:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21788msec
Apr 10 15:35:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:35:58 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 22288msec
Apr 10 15:35:58 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:35:59 [kernel] radeon 0000:00:10.0: Saved 160635 dwords of commands on ring 0.
Apr 10 15:35:59 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:35:59 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:35:59 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:35:59 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:35:59 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:35:59 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:35:59 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:35:59 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:36:09 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10148msec
Apr 10 15:36:09 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:09 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10648msec
Apr 10 15:36:09 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:10 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11148msec
Apr 10 15:36:10 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:10 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11648msec
Apr 10 15:36:10 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12148msec
Apr 10 15:36:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12648msec
Apr 10 15:36:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13148msec
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13648msec
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: Saved 109851 dwords of commands on ring 0.
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:36:12 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:36:12 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:36:12 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:36:12 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:36:12 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:36:23 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10492msec
Apr 10 15:36:23 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:23 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10992msec
Apr 10 15:36:23 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:24 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11492msec
Apr 10 15:36:24 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:24 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11992msec
Apr 10 15:36:24 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:25 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12492msec
Apr 10 15:36:25 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:25 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12992msec
Apr 10 15:36:25 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:26 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13492msec
Apr 10 15:36:26 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:26 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13992msec
Apr 10 15:36:26 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:27 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14492msec
Apr 10 15:36:27 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:27 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14992msec
Apr 10 15:36:27 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:28 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15492msec
Apr 10 15:36:28 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:28 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15992msec
Apr 10 15:36:28 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:29 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16492msec
Apr 10 15:36:29 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:29 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16992msec
Apr 10 15:36:29 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:30 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17492msec
Apr 10 15:36:30 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:30 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17992msec
Apr 10 15:36:30 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:31 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18492msec
Apr 10 15:36:31 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:31 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18992msec
Apr 10 15:36:31 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19492msec
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: Saved 59067 dwords of commands on ring 0.
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:36:32 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:36:32 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:36:32 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:36:32 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:36:32 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:36:42 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10228msec
Apr 10 15:36:42 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:43 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10728msec
Apr 10 15:36:43 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:43 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11228msec
Apr 10 15:36:43 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:44 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11728msec
Apr 10 15:36:44 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:44 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12228msec
Apr 10 15:36:44 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:45 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 12728msec
Apr 10 15:36:45 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:45 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13228msec
Apr 10 15:36:45 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:46 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 13728msec
Apr 10 15:36:46 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:46 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14228msec
Apr 10 15:36:46 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:47 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 14728msec
Apr 10 15:36:47 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:47 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15228msec
Apr 10 15:36:47 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:48 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 15728msec
Apr 10 15:36:48 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:48 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16228msec
Apr 10 15:36:48 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:49 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 16728msec
Apr 10 15:36:49 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:49 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17228msec
Apr 10 15:36:49 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:50 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 17728msec
Apr 10 15:36:50 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:50 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18228msec
Apr 10 15:36:50 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:51 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 18728msec
Apr 10 15:36:51 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:51 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19228msec
Apr 10 15:36:51 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:52 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 19728msec
Apr 10 15:36:52 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:52 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20228msec
Apr 10 15:36:52 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:53 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 20728msec
Apr 10 15:36:53 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:53 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21228msec
Apr 10 15:36:53 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:54 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 21728msec
Apr 10 15:36:54 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:54 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 22228msec
Apr 10 15:36:54 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:55 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 22728msec
Apr 10 15:36:55 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:55 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 23228msec
Apr 10 15:36:55 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:56 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 23728msec
Apr 10 15:36:56 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:56 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 24228msec
Apr 10 15:36:56 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 24728msec
Apr 10 15:36:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:57 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 25228msec
Apr 10 15:36:57 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:58 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 25728msec
Apr 10 15:36:58 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:58 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 26228msec
Apr 10 15:36:58 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:59 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 26728msec
Apr 10 15:36:59 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:36:59 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 27228msec
Apr 10 15:36:59 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 27728msec
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 28228msec
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(move mouse)
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: Saved 8283 dwords of commands on ring 0.
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: GPU reset succeeded, trying to resume
Apr 10 15:37:00 [kernel] [drm] PCI GART of 512M enabled (table at 0x000000002EF00000).
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: WB disabled
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: fence driver on ring 0 use gpu addr 0x0000000078000000 and cpu addr 0xeeea8000
Apr 10 15:37:00 [kernel] [drm] radeon: ring at 0x0000000078001000
Apr 10 15:37:00 [kernel] [drm:r100_ring_test] *ERROR* radeon: ring test failed (scratch(0x15E8)=0xCAFEDEAD)
Apr 10 15:37:00 [kernel] [drm:r100_cp_init] *ERROR* radeon: cp isn't working (-22).
Apr 10 15:37:00 [kernel] radeon 0000:00:10.0: failed initializing CP (-22).
Apr 10 15:37:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10364msec
Apr 10 15:37:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:37:11 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 10864msec
Apr 10 15:37:11 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
Apr 10 15:37:12 [kernel] radeon 0000:00:10.0: ring 0 stalled for more than 11364msec
Apr 10 15:37:12 [kernel] radeon 0000:00:10.0: GPU lockup (current fence id 0x0000000000002633 last fence id 0x0000000000002635 on ring 0)
(the previous two lines continue repeating every second or so, with the "saved ... dwords" sequence occurring every 30 seconds or so, unless I move the mouse, machine still responsive over SSH)
Comment 12 macro 2016-04-16 08:22:39 UTC
I have discovered that running

  Option "NoAccel" "True"

in xorg.conf "fixes" the problem, however I don't consider unaccelerated graphics an acceptable solution.

Does this in any way help narrow down where the real problem is?
Comment 13 erhard_f 2016-10-10 23:18:28 UTC
Now as my problem in Bug 97987 is solved I am facing this bug with the radeon driver. I use a r300 card, but the error messages are very similar so I decided not to open a new bug. Unlike the original bug report I am running a current 4.8.1-kernel, xorg-server-1.18.4, xf86-video-ati-7.7.1 and mesa-12.0.3.

Having said that Bug 95017, Bug 91893, Bug 96519 look seem very similar.

Sometimes the GPU can reset itself, most of the time I get a hard lock. If I use "radeon-agpmode=-1" as kernel parameter, X on my G5 holds out longer, but sooner or later I get a hard lock too.

dmesg-output:
[  774.360780] radeon 0000:f0:10.0: ring 0 stalled for more than 10443msec
[  774.360790] radeon 0000:f0:10.0: GPU lockup (current fence id 0x0000000000000407 last fence id 0x000000000000040e on ring 0)
[  774.511407] Failed to wait GUI idle while programming pipes. Bad things might happen.
[  774.512511] radeon 0000:f0:10.0: Saved 251 dwords of commands on ring 0.
[  774.512530] radeon 0000:f0:10.0: (r300_asic_reset:425) RBBM_STATUS=0x80010140
[  775.012522] radeon 0000:f0:10.0: (r300_asic_reset:444) RBBM_STATUS=0x80010140
[  775.508519] radeon 0000:f0:10.0: (r300_asic_reset:456) RBBM_STATUS=0x00000140
[  775.508551] radeon 0000:f0:10.0: GPU reset succeed
[  775.508556] radeon 0000:f0:10.0: GPU reset succeeded, trying to resume
[  775.508593] [drm] radeon: 1 quad pipes, 1 Z pipes initialized.
[  775.508601] radeon 0000:f0:10.0: WB disabled
[  775.508607] radeon 0000:f0:10.0: fence driver on ring 0 use gpu addr 0x0000000000000000 and cpu addr 0xd00000000139d000
[  775.508699] [drm] radeon: ring at 0x0000000000001000
[  775.508769] [drm] ring test succeeded in 0 usecs
[  775.559042] [drm] ib test succeeded in 0 usecs

What I also got is some interesting output in Xorg.0.log via sshd from another machine. Maybe this is of some help:

(EE) [mi] EQ overflowing.  Additional events will be discarded until existing events are processed.
(EE) 
(EE) Backtrace:
(EE) 0: /usr/bin/X (xorg_backtrace+0x6c) [0x101db7fc]
(EE) 1: /usr/bin/X (mieqEnqueue+0x2d0) [0x101b8eb0]
(EE) 2: /usr/bin/X (QueuePointerEvents+0x94) [0x10053254]
(EE) 3: /usr/bin/X (xf86PostMotionEventM+0x2dc) [0x10097adc]
(EE) 4: /usr/lib/xorg/modules/input/evdev_drv.so (0xcf6c000+0x4dd0) [0xcf70dd0]
(EE) 5: /usr/lib/xorg/modules/input/evdev_drv.so (0xcf6c000+0x56ac) [0xcf716ac]
(EE) 6: /usr/lib/xorg/modules/input/evdev_drv.so (0xcf6c000+0x5960) [0xcf71960]
(EE) 7: /usr/bin/X (0x10000000+0x848cc) [0x100848cc]
(EE) 8: /usr/bin/X (0x10000000+0xb3328) [0x100b3328]
(EE) 9: linux-vdso32.so.1 (__kernel_sigtramp32+0x0) [0x1003f4]
(EE) 10: /lib/libc.so.6 (ioctl+0xe8) [0xf9478d8]
(EE) 11: ?? [0x5b]
(EE) 12: /usr/lib/libdrm.so.2 (drmIoctl+0x54) [0xfd15484]
(EE) 13: /usr/lib/libdrm.so.2 (drmCommandWrite+0x38) [0xfd19618]
(EE) 14: /usr/lib/libdrm_radeon.so.1 (0xee9d000+0x17d8) [0xee9e7d8]
(EE) 15: /usr/lib/libdrm_radeon.so.1 (0xee9d000+0x1a98) [0xee9ea98]
(EE) 16: /usr/lib/libdrm_radeon.so.1 (radeon_bo_map+0x20) [0xeea06f0]
(EE) 17: /usr/lib/xorg/modules/drivers/radeon_drv.so (0xeece000+0x2e1e4) [0xeefc1e4]
(EE) 18: /usr/lib/xorg/modules/libexa.so (0xed68000+0x6130) [0xed6e130]
(EE) 19: /usr/lib/xorg/modules/libexa.so (0xed68000+0x8fd8) [0xed70fd8]
(EE) 20: /usr/lib/xorg/modules/libexa.so (0xed68000+0x137d0) [0xed7b7d0]
(EE) 21: /usr/lib/xorg/modules/libexa.so (0xed68000+0x10024) [0xed78024]
(EE) 22: /usr/bin/X (0x10000000+0x14fac8) [0x1014fac8]
(EE) 23: /usr/bin/X (CompositePicture+0x294) [0x1013c3f4]
(EE) 24: /usr/lib/xorg/modules/libexa.so (0xed68000+0x10ef0) [0xed78ef0]
(EE) 25: /usr/bin/X (CompositeTrapezoids+0xb8) [0x1013c6b8]
(EE) 26: /usr/bin/X (0x10000000+0x143330) [0x10143330]
(EE) 27: /usr/bin/X (0x10000000+0x13cb34) [0x1013cb34]
(EE) 28: /usr/bin/X (0x10000000+0x340cc) [0x100340cc]
(EE) 29: /usr/bin/X (0x10000000+0x38cac) [0x10038cac]
(EE) 30: /usr/bin/X (0x10000000+0x1e304) [0x1001e304]
(EE) 31: /lib/libc.so.6 (0xf855000+0x21414) [0xf876414]
(EE) 32: /lib/libc.so.6 (__libc_start_main+0xc0) [0xf8765d0]
(EE) 
(EE) [mi] These backtraces from mieqEnqueue may point to a culprit higher up the stack.
(EE) [mi] mieq is *NOT* the cause.  It is a victim.
[   775.542] [mi] Increasing EQ size to 1024 to prevent dropped events.
[   775.544] [mi] EQ processing has resumed after 85 dropped events.
[   775.544] [mi] This may be caused by a misbehaving driver monopolizing the server's resources.

If requested I can add full kernel config, Xorg.0.log and dmesg output. Or open a new bug if more appropriate.
Comment 14 Martin Peres 2019-11-19 07:56:08 UTC
-- 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/xorg/driver/xf86-video-ati/issues/157.

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.