[Bug 219399] System panics after several hours of 14-threads-compilation orgies using poudriere on AMD Ryzen...

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219399

--- Comment #9 from Andriy Gapon <avg at FreeBSD.org> ---
Nils,

I am not aware of any "mini test" that would be as good as a poudriere build or
a highly parallel buildworld.

I am not sure that the nvidia is really a culprit here, the stack frames beyond
the trap frame look rather messed up.  Maybe it's not that surprising given
that the original trap type is 0xc, #SS, Stack-Segment Fault.  Perhaps there
was a stack overflow.

If in kgdb you do 'list *0xffffffff831e410b', does it also point to _nv000224rm
?

The inability of kgdb to deal with the memory dump suggests a possibility of
critical page table structures being corrupt or a significant binary mismatch
between the userland (libkvm, etc) and the kernel.

FWIW, I found a bug report with somewhat similar backtrace, but it does not
have any enlightening details: bug #193622.

Perhaps a mismatch between the module and the kernel...

-- 
You are receiving this mail because:
You are the assignee for the bug.