Bug 71046

Summary:	GPU lockup on HD5470 with Brütal Legend
Product:	DRI	Reporter:	Johannes Hirte <johannes.hirte>
Component:	DRM/Radeon	Assignee:	Default DRI bug account <dri-devel>
Status:	RESOLVED DUPLICATE	QA Contact:
Severity:	normal
Priority:	medium
Version:	DRI git
Hardware:	Other
OS:	All
Whiteboard:
i915 platform:		i915 features:

Description Johannes Hirte 2013-10-30 12:15:17 UTC

Starting Brütal Legend works find during the intro, but when the game becomes interactive the screen is most times black. Only some times I get corrupted images from the game and in the log I found lots of this messages:

 Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: GPU lockup CP stall for more than 10001msec
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: GPU lockup (waiting for 0x0000000001a08c38 last fence id 0x0000000001a08c2d)
Oct 29 22:31:27 localhost kernel: [drm] Disabling audio 0 support
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: Saved 343 dwords of commands on ring 0.
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: GPU softreset: 0x00000009
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS               = 0xF7730828
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE0           = 0xFC000001
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE1           = 0x00000007
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS               = 0x20000AC0
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS2              = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008678_CP_STALLED_STAT2 = 0x400C0000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_00867C_CP_BUSY_STAT     = 0x00048002
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008680_CP_STAT          = 0x80268643
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_00D034_DMA_STATUS_REG   = 0x44C83D57
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: GRBM_SOFT_RESET=0x00007F6B
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: SRBM_SOFT_RESET=0x00000100
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS               = 0x00003828
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE0           = 0x00000007
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE1           = 0x00000007
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS               = 0x200000C0
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS2              = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008678_CP_STALLED_STAT2 = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_00867C_CP_BUSY_STAT     = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_008680_CP_STAT          = 0x00000000
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0:   R_00D034_DMA_STATUS_REG   = 0x44C83D57
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: GPU reset succeeded, trying to resume
Oct 29 22:31:27 localhost kernel: [drm] enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0
Oct 29 22:31:27 localhost kernel: [drm] PCIE GART of 1024M enabled (table at 0x000000000025D000).
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: WB enabled
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: fence driver on ring 0 use gpu addr 0x0000000020000c00 and cpu addr 0xffff8800de39cc00
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: fence driver on ring 3 use gpu addr 0x0000000020000c0c and cpu addr 0xffff8800de39cc0c
Oct 29 22:31:27 localhost kernel: radeon 0000:01:00.0: fence driver on ring 5 use gpu addr 0x000000000005c418 and cpu addr 0xffffc9000189c418
Oct 29 22:31:27 localhost kernel: [drm] ring test on 0 succeeded in 1 usecs
Oct 29 22:31:27 localhost kernel: [drm] ring test on 3 succeeded in 1 usecs
Oct 29 22:31:27 localhost kernel: [drm] ring test on 5 succeeded in 1 usecs
Oct 29 22:31:27 localhost kernel: [drm] UVD initialized successfully.
Oct 29 22:31:27 localhost kernel: [drm] Enabling audio 0 support
Oct 29 22:31:27 localhost kernel: [drm] ib test on ring 0 succeeded in 0 usecs
Oct 29 22:31:27 localhost kernel: [drm] ib test on ring 3 succeeded in 1 usecs
Oct 29 22:31:28 localhost kernel: [drm:uvd_v1_0_ib_test] *ERROR* radeon: failed to get create msg (-22).
Oct 29 22:31:28 localhost kernel: [drm:radeon_ib_ring_tests] *ERROR* radeon: failed testing IB on ring 5 (-22).
Oct 29 22:31:28 localhost kernel: switching from power state:
Oct 29 22:31:28 localhost kernel:       ui class: none
Oct 29 22:31:28 localhost kernel:       internal class: boot
Oct 29 22:31:28 localhost kernel:       caps: video
Oct 29 22:31:28 localhost kernel:       uvd    vclk: 0 dclk: 0
Oct 29 22:31:28 localhost kernel:               power level 0    sclk: 75000 mclk: 80000 vddc: 1120 vddci: 0
Oct 29 22:31:28 localhost kernel:               power level 1    sclk: 75000 mclk: 80000 vddc: 1120 vddci: 0
Oct 29 22:31:28 localhost kernel:               power level 2    sclk: 75000 mclk: 80000 vddc: 1120 vddci: 0
Oct 29 22:31:28 localhost kernel:       status: c b
Oct 29 22:31:28 localhost kernel: switching to power state:
Oct 29 22:31:28 localhost kernel:       ui class: performance
Oct 29 22:31:28 localhost kernel:       internal class: none
Oct 29 22:31:28 localhost kernel:       caps: single_disp video
Oct 29 22:31:28 localhost kernel:       uvd    vclk: 0 dclk: 0
Oct 29 22:31:28 localhost kernel:               power level 0    sclk: 15700 mclk: 20000 vddc: 900 vddci: 0
Oct 29 22:31:28 localhost kernel:               power level 1    sclk: 40000 mclk: 50000 vddc: 900 vddci: 0
Oct 29 22:31:28 localhost kernel:               power level 2    sclk: 75000 mclk: 80000 vddc: 1120 vddci: 0
Oct 29 22:31:28 localhost kernel:       status: r
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: GPU lockup CP stall for more than 10000msec
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: GPU lockup (waiting for 0x0000000001a08c4b last fence id 0x0000000001a08c43)
Oct 29 22:31:39 localhost kernel: [drm] Disabling audio 0 support
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: Saved 535 dwords of commands on ring 0.
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: GPU softreset: 0x00000009
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS               = 0xE7730828
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE0           = 0xFC000001
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE1           = 0x00000007
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS               = 0x200000C0
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS2              = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008678_CP_STALLED_STAT2 = 0x00010800
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_00867C_CP_BUSY_STAT     = 0x00028006
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008680_CP_STAT          = 0x80038647
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_00D034_DMA_STATUS_REG   = 0x44C83D57
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: GRBM_SOFT_RESET=0x00007F6B
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: SRBM_SOFT_RESET=0x00000100
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS               = 0x00003828
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE0           = 0x00000007
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   GRBM_STATUS_SE1           = 0x00000007
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS               = 0x200000C0
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   SRBM_STATUS2              = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008678_CP_STALLED_STAT2 = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_00867C_CP_BUSY_STAT     = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_008680_CP_STAT          = 0x00000000
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0:   R_00D034_DMA_STATUS_REG   = 0x44C83D57
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: GPU reset succeeded, trying to resume
Oct 29 22:31:39 localhost kernel: [drm] enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0
Oct 29 22:31:39 localhost kernel: [drm] PCIE GART of 1024M enabled (table at 0x000000000025D000).
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: WB enabled
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: fence driver on ring 0 use gpu addr 0x0000000020000c00 and cpu addr 0xffff8800de39cc00
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: fence driver on ring 3 use gpu addr 0x0000000020000c0c and cpu addr 0xffff8800de39cc0c
Oct 29 22:31:39 localhost kernel: radeon 0000:01:00.0: fence driver on ring 5 use gpu addr 0x000000000005c418 and cpu addr 0xffffc9000189c418
Oct 29 22:31:39 localhost kernel: [drm] ring test on 0 succeeded in 1 usecs
Oct 29 22:31:39 localhost kernel: [drm] ring test on 3 succeeded in 1 usecs
Oct 29 22:31:39 localhost kernel: [drm] ring test on 5 succeeded in 1 usecs
Oct 29 22:31:39 localhost kernel: [drm] UVD initialized successfully.
Oct 29 22:31:39 localhost kernel: [drm] Enabling audio 0 support

I can kill the game from console and the system seems to work fine afterwards.

Comment 1 Johannes Hirte 2013-10-30 12:16:31 UTC

Forgotten: kernel is 3.12-rc7 and mesa is from git.

Comment 2 Alex Deucher 2013-10-30 13:00:33 UTC

Does disabling hyperZ help?  Set env var R600_HYPERZ=0

This is probably a duplicate of bug 64471.

Comment 3 Johannes Hirte 2013-10-30 14:13:10 UTC

Yes, seems to be the same problem. Disabling hyperZ fixes the lockups but there are still graphic corruptions.

Comment 4 Alex Deucher 2013-10-30 14:14:17 UTC


*** This bug has been marked as a duplicate of bug 64471 ***

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.