Messages in this thread | | | Subject | Re: Opinion on ordering of writel vs. stores to RAM | From | Jes Sorensen <> | Date | 11 Sep 2006 09:19:36 -0400 |
| |
>>>>> "Ben" == Benjamin Herrenschmidt <benh@kernel.crashing.org> writes:
Ben> On Sun, 2006-09-10 at 23:23 +0100, Alan Cox wrote: >> Ar Llu, 2006-09-11 am 07:25 +1000, ysgrifennodd Benjamin >> Herrenschmidt: > I'm copying that from a private discussion I >> had. Please let me know if > you have comments. This proposal >> includes some questions too so please > answer :) >> >> Looks sane and Linus seems to like mmiowb. Only other question: >> what are the guarantees of memcpy_to/fromio. Does it access the >> memory in ordered fashion or not, does it guarantee only ordering >> at the end of the copy or during it ?
Ben> Well, Linus is also ok with writel not ordering memory an IO Ben> accesses :) Though he also mentioned that if we go that route Ben> (which is what we have now in fact), we take the burden of having Ben> to test and fix drivers who don't get it...
We have to do this on SN2 anyway, so this way we can benefit from each other's work :)
Cheers, Jes - 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/
| |