(In reply to Andy Furniss from comment #24)
> (In reply to Andy Furniss from comment #23)
> 
> > I haven't seen thousands until Today so that aspect could be to do with the
> > patches.
> 
> Ignore that, more grepping of kernel log does show I have got thousands
> before today.

Haven't had time to test thoroughly, but I see the latest updated agd5f fixes
has a commit to reduce vm faults and I haven't got thousands since changing to
that.

I also see a new R600_DEBUG=check_vm in mesa. I don't know what, if any, extra
info is expected from that, but testing valley with it caused it to quit when
it hit a fault after a about minute of running -

Detected a VM fault, exiting...

in dmesg -

[  261.017278] amdgpu 0000:01:00.0: GPU fault detected: 146 0x01e84804
[  261.017290] amdgpu 0000:01:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR  
0x0015703D
[  261.017296] amdgpu 0000:01:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS
0x06048004
[  261.017302] VM fault (0x04, vmid 3) at page 1404989, read from 'TC6'
(0x54433600) (72)