On Fri, 2011-02-04 at 15:39 -0500, Chris Metcalf wrote: > On 1/25/2011 12:31 PM, Peter Zijlstra wrote: > > Tile's __pte_free_tlb() implementation makes assumptions about the > > generic mmu_gather implementation, cure this ;-) > > I assume you will take this patch into your tree? If so: > > Acked-by: Chris Metcalf <cmetcalf@xxxxxxxxxx> Feel free to take it yourself, this series might take a while to land.. > > [ Chris, from a quick look L2_USER_PGTABLE_PAGES is something like: > > 1 << (24 - 16 + 3), which looks awefully large for an on-stack > > array. ] > > Yes, the pte_pages[] array in this routine is 2KB currently. Currently we > ship with 64KB pagesize, so the kernel stack has plenty of room. I do like > that your patch removes this buffer, however, since we're currently looking > into (re-)supporting 4KB pages, which would totally blow the kernel stack > in this routine. Ah, ok. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>