Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- From: Bryan O'Sullivan <bos@xxxxxxxxxxxxx>
- Date: Wed, 08 Mar 2006 13:57:54 -0800
On Wed, 2006-03-08 at 15:21 +0100, Andi Kleen wrote:
I think doing it privately is the better solution because I don't think you
have established it has an universal semantic that works
on all X86-64 systems.
No, I quoted chapter and verse of the relevant Intel and AMD x86_64 docs
for you, complete with URLs and page numbers so it wouldn't take any
effort to verify what I was asserting.
I don't know what else I could have done (it was enough for bcrl, at
least), and you have come up any with suggestions as to what *would*
satisfy you, so I'm stuck.
And we don't have a portable way to do WC anyways, so there is
no portable way to use it.
So just put an ifdef in.
That's fine. Whatever satisfies reviewers :-)
<b
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
- Follow-Ups:
- References:
- [PATCH] Define flush_wc, a way to flush write combining store buffers
- From: Bryan O'Sullivan
- Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- From: Benjamin Herrenschmidt
- Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- From: Bryan O'Sullivan
- Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- From: Andi Kleen
- [PATCH] Define flush_wc, a way to flush write combining store buffers
- Prev by Date: Re: 2.6.15-rt20, "bad page state", jackd
- Next by Date: Re: proper way to assign fixed PCI resources to a "hotplug" device
- Previous by thread: Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- Next by thread: Re: [PATCH] Define flush_wc, a way to flush write combining store buffers
- Index(es):