Messages in this thread | | | Date | Tue, 12 Sep 2006 03:21:03 -0400 | From | "Albert Cahalan" <> | Subject | Re: Opinion on ordering of writel vs. stores to RAM |
| |
On 9/12/06, Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote: > > > If I see an io_to_io_barrier(), how am I to tell if it is > > read to read, write to write, read to write, write to read, > > read/write to read, read/write to write, read to read/write, > > write to read/write, or read/write to read/write? > > > > Considering just reads and writes to MMIO, there are > > 9 possible types of fence. SPARC seems to cover a > > decent number of these distinctly; the instruction takes > > an immediate value as flags. > > We need to decide wether a single one doing a full MMIO fence (and not > memory) is enough or if the performance different justifies maybe having > io_to_io_{wmb,rmb,mb}. I don't see any real use for more combinations.
Remember: it's more than just performance. It's documentation in the code. - 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/
| |