Messages in this thread | | | Date | Fri, 2 Apr 2004 20:54:10 +0100 | From | Christoph Hellwig <> | Subject | Re: [RFC][PATCH 1/3] radix priority search tree - objrmap complexity fix |
| |
On Fri, Apr 02, 2004 at 09:29:41PM +0200, Andrea Arcangeli wrote: > page->private indicates: > > >>> (0xc0772380L-0xc07721ffL)/32 > 12L > > that's the 12th page in the array. > > can you check in the asm (you should look at address c0048c7c) if it's > the first bug that triggers? > > if (page[1].index != order) > bad_page(__FUNCTION__, page);
No, it's the second one (and yes, I get lots of theses backtraces, unless I counted wrongly 19 this time)
> the whole compound thing is very screwed in the above scenario. > > Do you have CONFIG_DEBUG_PAGEALLOC enabled?
no. it's not available on ppc32.
> could be compound never worked right on ppc, dunno. You could try to > backout the patch gfp-no-compound and to recompile with hugetlbfs > enabled (can you enable it on PPC?).
no, there's no hugetlb support on ppc32.
- 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/
| |