* Miguel Botón <mboton.lkml@gmail.com> wrote:

quoted text
> These hardlocks start to appear with commit 
> f10c1cfd359660c01446807b6c2bc8ce3aee919a

thanks, that's really useful! I dont see anything obviously wrong with 
the commit though, and cannot (yet) reproduce it, so to help us track it 
down further, could you try to figure out the lockup site? Does the NMI 
watchdog work on your box?

if the NMI watchdog does not work, can you reproduce it on a VGA 
console? If yes, then running the app that does the hard lockup via 
"strace -f <app>" could perhaps show us the last system call that 
happened before the box locked up. If we are lucky it's something 
specific.

here's the guilty commit from latest x86.git#mm:

  commit 81376371f1ca371de54aa4488edc541580d95a01
  Author: Roland McGrath <roland@redhat.com>
  Date:   Tue Jan 1 21:55:28 2008 +0100

      x86 i387 user_regset

	Ingo
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/