amdgpu 0000:01:00.0: IH ring buffer overflow (0x00000010, 0x00000000, 0x00000020)

[Paul Menzel]

Dear Linux AMD folks,


I get the overrun message below.

> $ more /proc/version
> Linux version 4.14.30.mx64.211 (root at holidayincambodia.molgen.mpg.de) (gcc version 7.3.0 (GCC)) #1 SMP Tue Mar 27 12:40:07 CEST 2018
> $ lspci -s 01:00.0
> 01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Bonaire [FirePro W5100]
> $ dmesg | grep amdgpu
> [   12.382379] [drm] amdgpu kernel modesetting enabled.
> [   12.419916] amdgpu 0000:01:00.0: VRAM: 4096M 0x000000F400000000 - 0x000000F4FFFFFFFF (4096M used)
> [   12.420681] amdgpu 0000:01:00.0: GTT: 1024M 0x0000000000000000 - 0x000000003FFFFFFF
> [   12.424246] [drm] amdgpu: 4096M of VRAM memory ready
> [   12.424682] [drm] amdgpu: 4096M of GTT memory ready.
> [   12.427912] amdgpu 0000:01:00.0: amdgpu: using MSI.
> [   12.428389] [drm] amdgpu: irq initialized.
> [   12.439899] [drm] amdgpu: dpm initialized
> [   12.501392] amdgpu 0000:01:00.0: fence driver on ring 0 use gpu addr 0x0000000000400080, cpu addr 0xffffc90002c25080
> [   12.502433] amdgpu 0000:01:00.0: fence driver on ring 1 use gpu addr 0x0000000000400100, cpu addr 0xffffc90002c25100
> [   12.503412] amdgpu 0000:01:00.0: fence driver on ring 2 use gpu addr 0x0000000000400180, cpu addr 0xffffc90002c25180
> [   12.504440] amdgpu 0000:01:00.0: fence driver on ring 3 use gpu addr 0x0000000000400200, cpu addr 0xffffc90002c25200
> [   12.505378] amdgpu 0000:01:00.0: fence driver on ring 4 use gpu addr 0x0000000000400280, cpu addr 0xffffc90002c25280
> [   12.506438] amdgpu 0000:01:00.0: fence driver on ring 5 use gpu addr 0x0000000000400300, cpu addr 0xffffc90002c25300
> [   12.507474] amdgpu 0000:01:00.0: fence driver on ring 6 use gpu addr 0x0000000000400380, cpu addr 0xffffc90002c25380
> [   12.508579] amdgpu 0000:01:00.0: fence driver on ring 7 use gpu addr 0x0000000000400400, cpu addr 0xffffc90002c25400
> [   12.509629] amdgpu 0000:01:00.0: fence driver on ring 8 use gpu addr 0x0000000000400480, cpu addr 0xffffc90002c25480
> [   12.511172] amdgpu 0000:01:00.0: fence driver on ring 9 use gpu addr 0x0000000000400500, cpu addr 0xffffc90002c25500
> [   12.512211] amdgpu 0000:01:00.0: fence driver on ring 10 use gpu addr 0x0000000000400580, cpu addr 0xffffc90002c25580
> [   12.521048] amdgpu 0000:01:00.0: fence driver on ring 11 use gpu addr 0x000000f40028bd30, cpu addr 0xffffc90003638d30
> [   12.523287] amdgpu 0000:01:00.0: fence driver on ring 12 use gpu addr 0x0000000000400680, cpu addr 0xffffc90002c25680
> [   12.524345] amdgpu 0000:01:00.0: fence driver on ring 13 use gpu addr 0x0000000000400700, cpu addr 0xffffc90002c25700
> [   12.823525] fbcon: amdgpudrmfb (fb0) is primary device
> [   13.089730] amdgpu 0000:01:00.0: fb0: amdgpudrmfb frame buffer device
> [   13.097141] [drm] Initialized amdgpu 3.19.0 20150101 for 0000:01:00.0 on minor 1
> [90612.637194] amdgpu 0000:01:00.0: IH ring buffer overflow (0x00000010, 0x00000000, 0x00000020)

Should this be reported and fixed? How can this be debugged? 
(`drm.debug=0xe`?). We do not know how to reproduce it yet.


Kind regards,

Paul

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 5174 bytes
Desc: S/MIME Cryptographic Signature
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20180427/a5db601f/attachment.bin>