GPU lockup CP stall for more than 10000msec on latest vanilla git

[Markus Trippelsdorf]

On 2012.12.23 at 10:09 +0000, Andy Furniss wrote:
> Markus Trippelsdorf wrote:
> 
> >> Does booting with radeon.wb=0 fix the issue?  Please make sure your
> >> kernel has this patch:
> >> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=commitdiff;h=86a1881d08f65a42c17071a59c0088dbe2870246
> >
> > My kernel has this patch and radeon.wb=0 doesn't help.
> 
> I think that should be no_wb=1

Yes, you're right. But even with radeon.no_wb=1 it still hangs:


...
Dec 23 11:15:02 x4 kernel: radeon 0000:01:05.0: WB disabled
Dec 23 11:15:02 x4 kernel: radeon 0000:01:05.0: fence driver on ring 0 use gpu addr 0x00000000a0000004 and cpu addr 0xffff8802163ad004
Dec 23 11:15:02 x4 kernel: radeon 0000:01:05.0: fence driver on ring 3 use gpu addr 0x00000000a0000c0c and cpu addr 0xffff8802163adc0c
Dec 23 11:15:02 x4 kernel: radeon 0000:01:05.0: setting latency timer to 64
...
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: GPU lockup CP stall for more than 10000msec
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: GPU lockup (waiting for 0x000000000000089c last fence id 0x000000000000089b)
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: Saved 217 dwords of commands on ring 0.
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: GPU softreset 
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008010_GRBM_STATUS=0xA000B030
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008014_GRBM_STATUS2=0x00000003
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_000E50_SRBM_STATUS=0x20005040
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008678_CP_STALLED_STAT2 = 0x00000002
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_00867C_CP_BUSY_STAT     = 0x0000D086
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008680_CP_STAT          = 0x80098645
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008020_GRBM_SOFT_RESET=0x00007FEE
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: R_008020_GRBM_SOFT_RESET=0x00000001
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008010_GRBM_STATUS=0xA000B030
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008014_GRBM_STATUS2=0x00000003
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_000E50_SRBM_STATUS=0x2000C040
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008678_CP_STALLED_STAT2 = 0x00000000
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_00867C_CP_BUSY_STAT     = 0x00000000
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0:   R_008680_CP_STAT          = 0x80100000
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: GPU reset succeeded, trying to resume
Dec 23 11:16:04 x4 kernel: [drm] PCIE GART of 512M enabled (table at 0x00000000C0040000).
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: WB disabled
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: fence driver on ring 0 use gpu addr 0x00000000a0000004 and cpu addr 0xffff8802163ad004
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: fence driver on ring 3 use gpu addr 0x00000000a0000c0c and cpu addr 0xffff8802163adc0c
Dec 23 11:16:04 x4 kernel: radeon 0000:01:05.0: setting latency timer to 64
Dec 23 11:16:04 x4 kernel: [drm] ring test on 0 succeeded in 1 usecs
Dec 23 11:16:05 x4 kernel: [drm:r600_dma_ring_test] *ERROR* radeon: ring 3 test failed (0xCAFEDEAD)
Dec 23 11:16:05 x4 kernel: [drm:r600_resume] *ERROR* r600 startup failed on resume
Dec 23 11:16:09 x4 kernel: SysRq : Emergency Sync
Dec 23 11:16:09 x4 kernel: Emergency Sync complete
Dec 23 11:16:15 x4 kernel: SysRq : Emergency Remount R/O
Dec 23 11:16:15 x4 kernel: EXT4-fs (sdb2): re-mounted. Opts: (null)

-- 
Markus