Messages in this thread | | | Date | Fri, 6 Jul 2007 18:50:06 +0900 | From | KAMEZAWA Hiroyuki <> | Subject | Re: [BUGFIX]{PATCH] flush icache on ia64 take2 |
| |
On Fri, 06 Jul 2007 11:41:38 +0200 Zoltan Menyhart <Zoltan.Menyhart@bull.net> wrote:
> KAMEZAWA Hiroyuki wrote: > > > Note1: icache flush is called only when VM_EXEC flag is on and > > PG_arch_1 is not set. > > If you have not got the page in the cache, then the new page will > be allocated with PG_arch_1 bit off. > You are going to flush pages which are read by HW DMA, i.e. the L2I > of Montecito does not keep old lines for those pages anyway. > yes, it's my concern.
> ...->a_ops->readpage() of "L2I safe" file systems should set PG_arch_1 > if the CPU is ia64 and it has got separate L2I. > > On the other hand, arch. independent file systems should not play with > PG_arch_1. > The base kernel should export a macro for the file systems... > Hm, but it should be discussed in another thread... I think. From memory management view, flush_icache before set_pte() is sane thing.
-Kame
- 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/
| |