Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Paul Mackerras
Mike Kravetz writes: > Thanks for the debug work! Just curious if you really need > CONFIG_NODES_SPAN_OTHER_NODES defined for your platform? Can you get > those types of memory layouts? If not, an easy/immediate fix for you > might be to simply turn off the option. We really need

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Arnd Bergmann
On Thursday 14 December 2006 00:17, Mike Kravetz wrote: > Thanks for the debug work!  Just curious if you really need > CONFIG_NODES_SPAN_OTHER_NODES defined for your platform?  Can you get > those types of memory layouts?  If not, an easy/immediate fix for you > might be to simply turn off the

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Benjamin Herrenschmidt
> Thanks for the debug work! Just curious if you really need > CONFIG_NODES_SPAN_OTHER_NODES defined for your platform? Can you get > those types of memory layouts? If not, an easy/immediate fix for you > might be to simply turn off the option. Yes, we need that for some pSeries boxes. Ben.

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Mike Kravetz
On Wed, Dec 13, 2006 at 07:20:57PM +0100, Arnd Bergmann wrote: > After a lot of debugging in spufs, I found that a crash that we encountered > on Cell actually was caused by a change in the memory management. > > The patch that caused it is archived in http://lkml.org/lkml/2006/11/1/43, > and

Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Arnd Bergmann
After a lot of debugging in spufs, I found that a crash that we encountered on Cell actually was caused by a change in the memory management. The patch that caused it is archived in http://lkml.org/lkml/2006/11/1/43, and this one has been discussed back and forth, but I fear that the current

Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Arnd Bergmann
After a lot of debugging in spufs, I found that a crash that we encountered on Cell actually was caused by a change in the memory management. The patch that caused it is archived in http://lkml.org/lkml/2006/11/1/43, and this one has been discussed back and forth, but I fear that the current

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Mike Kravetz
On Wed, Dec 13, 2006 at 07:20:57PM +0100, Arnd Bergmann wrote: After a lot of debugging in spufs, I found that a crash that we encountered on Cell actually was caused by a change in the memory management. The patch that caused it is archived in http://lkml.org/lkml/2006/11/1/43, and this one

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Benjamin Herrenschmidt
Thanks for the debug work! Just curious if you really need CONFIG_NODES_SPAN_OTHER_NODES defined for your platform? Can you get those types of memory layouts? If not, an easy/immediate fix for you might be to simply turn off the option. Yes, we need that for some pSeries boxes. Ben. -

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Arnd Bergmann
On Thursday 14 December 2006 00:17, Mike Kravetz wrote: Thanks for the debug work!  Just curious if you really need CONFIG_NODES_SPAN_OTHER_NODES defined for your platform?  Can you get those types of memory layouts?  If not, an easy/immediate fix for you might be to simply turn off the

Re: Bug: early_pfn_in_nid() called when not early

2006-12-13 Thread Paul Mackerras
Mike Kravetz writes: Thanks for the debug work! Just curious if you really need CONFIG_NODES_SPAN_OTHER_NODES defined for your platform? Can you get those types of memory layouts? If not, an easy/immediate fix for you might be to simply turn off the option. We really need